INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

iframe

-0.83

SOURCE

-0.78

LIST

-0.75

stocks

-0.73

reon

-0.73

stuff

-0.69

atche

-0.69

Sov

-0.68

thens

-0.67

ufact

-0.66

POSITIVE LOGITS

 Racing

0.74

 Masters

0.67

 Licensed

0.66

rollers

0.66

 touchdown

0.62

Pic

0.62

 Negro

0.62

 Protestant

0.61

ienne

0.61

arson

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.