INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

 Others

-0.69

ICLE

-0.69

 Amos

-0.66

FIELD

-0.65

 weed

-0.62

BDS

-0.62

HF

-0.61

GGGG

-0.61

RANT

-0.60

 steroids

-0.60

POSITIVE LOGITS

untary

0.73

apter

0.72

asio

0.66

 mailing

0.65

udeau

0.65

castle

0.65

eco

0.64

 unden

0.64

ãĥ¯

0.64

mitt

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.