INDEX

Explanations

mentions of political figures named "Muammar" with differing activations suggesting a focus on specific instances or elements related to the individual throughout the text

oai_token-act-pair · gpt-3.5-turbo

references to the name "Muammar."

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ä»£

-0.90

Peb

-0.71

OME

-0.69

EMS

-0.69

CAST

-0.67

 Dispatch

-0.66

 Dangerous

-0.65

peak

-0.65

 pans

-0.64

arantine

-0.63

POSITIVE LOGITS

riages

1.07

quez

0.88

iously

0.87

ques

0.85

anth

0.81

zynski

0.79

iam

0.78

rying

0.76

quet

0.76

ital

0.75

Activations Density 0.009%

mentions of political figures named "Muammar" with differing activations suggesting a focus on specific instances or elements related to the individual throughout the text

references to the name "Muammar."

No Comments

No Known Activations