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

 Awakening

-0.69

 Song

-0.68

ãĥĹ

-0.67

osponsors

-0.66

aurus

-0.63

gotten

-0.63

iquette

-0.62

HUN

-0.62

Hun

-0.61

ichick

-0.59

POSITIVE LOGITS

pse

0.76

 smoot

0.71

 dressing

0.71

ilated

0.66

repre

0.66

 defe

0.65

 smear

0.65

ÂłÂłÂłÂłÂłÂłÂłÂł

0.65

 marqu

0.65

doctor

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.