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

BLIC

-0.88

TAG

-0.81

rontal

-0.79

âķĲâķĲ

-0.77

Revolution

-0.74

ãĥķãĤ©

-0.72

amins

-0.69

uren

-0.69

GAN

-0.68

alid

-0.68

POSITIVE LOGITS

ocaust

0.78

 quotes

0.74

 vividly

0.65

xual

0.64

 prejudice

0.63

 ejected

0.62

selection

0.62

 expelled

0.62

.''.

0.61

igrants

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.