INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

obl

-0.73

itbart

-0.72

osaurus

-0.70

 corrid

-0.70

alog

-0.69

ŃĶ

-0.69

indal

-0.66

 plurality

-0.66

angs

-0.65

acons

-0.65

POSITIVE LOGITS

 Debor

0.68

sky

0.68

 rehears

0.65

 Turing

0.63

ueless

0.63

Ranked

0.63

Ago

0.62

@@

0.61

@@

0.60

hai

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.