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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

©

-0.78

»Ĵ

-0.73

lihood

-0.72

ozo

-0.72

 compr

-0.70

merce

-0.67

 dstg

-0.66

 Scholars

-0.65

onymous

-0.65

hovah

-0.65

POSITIVE LOGITS

 tilt

0.86

Marginal

0.71

 hydra

0.69

nar

0.64

ibility

0.64

 Clause

0.63

camp

0.63

ship

0.62

RFC

0.61

NAT

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.