INDEX

Explanations

statistical data related to performance metrics

oai_token-act-pair · gpt-3.5-turbo

occurrences of statistical data or numerical figures

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

 Constantin

-0.74

 Survivors

-0.69

 Hills

-0.67

 Kurd

-0.67

 Samar

-0.67

 Ancients

-0.65

 Lomb

-0.65

 Sylv

-0.64

 Wend

-0.64

 Berry

-0.64

POSITIVE LOGITS

/.

0.90

icago

0.89

0.82

ãĥĺ

0.81

etc

0.80

olitics

0.79

ãĥĪ

0.77

STAT

0.77

 cubic

0.75

Pg

0.75

Activations Density 0.007%

statistical data related to performance metrics

occurrences of statistical data or numerical figures

No Comments

No Known Activations