INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

nces

-0.75

terness

-0.72

 comparisons

-0.69

ramer

-0.65

INO

-0.62

banks

-0.61

 substr

-0.61

SPONSORED

-0.61

Ing

-0.61

————

-0.60

POSITIVE LOGITS

ride

0.64

 coffin

0.64

oire

0.64

 Brig

0.62

 Nare

0.62

wall

0.61

iful

0.61

 Tide

0.59

 curtain

0.58

anmar

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.