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

éĹĺ

-0.66

acion

-0.66

ofi

-0.65

ware

-0.65

 toolbar

-0.62

ä½ľ

-0.62

relation

-0.61

 CLSID

-0.60

abiding

-0.60

urations

-0.60

POSITIVE LOGITS

zu

0.76

zo

0.72

reviewed

0.68

orset

0.65

uzz

0.65

uca

0.63

ps

0.63

heny

0.62

iosyncr

0.61

thumbnails

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.