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

 seam

-0.77

 compressor

-0.72

£ı

-0.71

 Indra

-0.69

 commissioned

-0.68

 feasibility

-0.66

psy

-0.63

 probe

-0.63

pH

-0.63

 transformer

-0.62

POSITIVE LOGITS

Vote

0.87

irements

0.79

ember

0.76

clus

0.73

Newsletter

0.71

ombat

0.70

ONT

0.70

Northern

0.69

IRE

0.69

ater

0.69

Activations Density 0.000%

No Known Activations

This feature has no known activations.