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

rils

-0.95

pex

-0.83

aline

-0.80

rams

-0.79

daq

-0.70

umi

-0.69

rin

-0.67

riel

-0.67

 oxide

-0.66

REF

-0.65

POSITIVE LOGITS

 Austral

0.80

Maj

0.70

plex

0.69

 Conserv

0.65

 honor

0.62

 Gent

0.62

Austral

0.61

 Brach

0.60

bid

0.59

 Curve

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.