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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

renheit

-0.91

verty

-0.84

ivals

-0.83

rador

-0.81

verbs

-0.81

yip

-0.81

elong

-0.78

interrupted

-0.78

alogue

-0.77

thood

-0.76

POSITIVE LOGITS

 Radeon

0.74

orc

0.68

 tattoo

0.63

Patch

0.63

 Mull

0.62

 Morph

0.61

Rx

0.60

 Planes

0.58

 arsenal

0.58

 Targ

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.