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

 millenn

-0.77

dayName

-0.75

AppData

-0.70

unal

-0.70

 Secondly

-0.70

ares

-0.70

soType

-0.69

 unden

-0.68

????????

-0.66

anches

-0.65

POSITIVE LOGITS

 outnumbered

0.68

keeper

0.68

 Sachs

0.68

press

0.65

icho

0.63

 tilted

0.57

 undercut

0.56

pressed

0.56

 weakened

0.56

iologist

0.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.