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

quickShipAvailable

-0.85

etheless

-0.79

kinson

-0.76

heit

-0.71

 Participant

-0.70

unin

-0.66

enance

-0.66

ynes

-0.66

imore

-0.65

ueller

-0.65

POSITIVE LOGITS

ativity

0.70

eworld

0.64

ammy

0.64

arium

0.62

edia

0.61

 council

0.59

 landmarks

0.58

agra

0.58

gallery

0.58

unctions

0.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.