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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

obyl

-0.81

opsis

-0.73

 Depth

-0.70

cro

-0.70

oid

-0.69

 Psych

-0.68

ã

-0.68

ror

-0.68

 Psychiat

-0.65

ogly

-0.64

POSITIVE LOGITS

SPONSORED

0.90

cake

0.75

cheat

0.66

 Rolls

0.66

 pleas

0.64

 craw

0.63

pite

0.63

 progress

0.63

 vain

0.62

 cheating

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.