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

 Avalanche

-0.68

STR

-0.66

Tes

-0.64

Thunder

-0.63

wat

-0.62

 Mong

-0.62

————

-0.62

ãĤ£

-0.62

eely

-0.62

Agg

-0.61

POSITIVE LOGITS

housing

0.83

 offending

0.73

eport

0.72

terness

0.70

 marketed

0.69

 heights

0.65

 offender

0.65

iaries

0.65

 licens

0.65

 mortgages

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.