INDEX

Explanations

references to a specific sports team named "Jets."

oai_token-act-pair · gpt-3.5-turbo

mentions of the "Jets," likely indicating a focus on a sports team

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

istically

-0.74

istic

-0.74

istics

-0.73

ances

-0.67

 fide

-0.67

ists

-0.67

Trigger

-0.67

EngineDebug

-0.66

 advoc

-0.66

holder

-0.65

POSITIVE LOGITS

 Jets

0.96

pps

0.76

rod

0.74

awar

0.74

peak

0.74

ouls

0.73

eco

0.72

chedel

0.71

onic

0.70

 Stadium

0.69

Activations Density 0.013%

references to a specific sports team named "Jets."

mentions of the "Jets," likely indicating a focus on a sports team

No Comments

No Known Activations