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

gas

-0.72

multipl

-0.68

behind

-0.65

Route

-0.65

mess

-0.65

Prop

-0.64

Gas

-0.63

-0.62

hash

-0.61

 versa

-0.61

POSITIVE LOGITS

ework

0.77

wana

0.73

riter

0.71

 millenn

0.66

Ħ¢

0.66

 Madden

0.65

VIDIA

0.63

AD

0.62

aspers

0.62

 Democr

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.