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

kj

-0.69

 mediated

-0.67

gary

-0.66

leigh

-0.65

ram

-0.64

odcast

-0.63

aul

-0.63

 joke

-0.62

Ì

-0.61

 talks

-0.60

POSITIVE LOGITS

ĳå£«

0.93

 Adventure

0.89

avorite

0.78

ordinary

0.75

adobe

0.71

 Decay

0.69

ilant

0.68

URA

0.66

IFE

0.66

 srfAttach

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.