INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

heed

-0.75

 cues

-0.66

 cassette

-0.65

het

-0.64

rum

-0.64

 clipboard

-0.64

iker

-0.63

rys

-0.62

hn

-0.61

epad

-0.60

POSITIVE LOGITS

å§«

0.77

ãĤ©

0.73

 Results

0.71

Ô

0.71

à¹

0.70

 Result

0.68

),"

0.67

autions

0.65

 Otherwise

0.65

ITION

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.