INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

flix

-0.70

HUD

-0.70

 Laksh

-0.66

icum

-0.64

videos

-0.63

HY

-0.62

 elig

-0.62

Ĥ¬

-0.57

iframe

-0.57

atha

-0.57

POSITIVE LOGITS

cius

0.72

iferation

0.72

imov

0.67

 Hundred

0.66

ansk

0.63

hran

0.62

cart

0.62

gencies

0.62

comfort

0.61

algia

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.