INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

hester

-0.84

cientious

-0.84

lins

-0.83

uay

-0.81

itus

-0.79

abilia

-0.79

amina

-0.78

umption

-0.78

idth

-0.77

atem

-0.76

POSITIVE LOGITS

cry

0.69

qs

0.69

 weep

0.69

 Siri

0.68

 mashed

0.62

 blinded

0.60

 snap

0.59

 Aviv

0.58

 shout

0.58

ksh

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.