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

hee

-0.72

etts

-0.71

shr

-0.66

adelphia

-0.64

essen

-0.64

thia

-0.64

orgetown

-0.63

Gaza

-0.63

abee

-0.62

annon

-0.61

POSITIVE LOGITS

 describ

0.73

emis

0.68

 peers

0.65

 advers

0.64

iamond

0.64

hed

0.64

romeda

0.63

 mates

0.63

uno

0.63

uin

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.