INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 rumors

-0.59

 drummer

-0.58

 Salam

-0.56

 frontman

-0.55

 Vers

-0.55

 Saudis

-0.54

 liberating

-0.53

 policemen

-0.52

 Revelations

-0.52

 Lana

-0.52

POSITIVE LOGITS

1.25

.?

0.90

*.

0.89

.(

0.89

.''.

0.86

.","

0.83

.}

0.83

uckland

0.82

!.

0.82

.:

0.80

Activations Density 0.000%

No Known Activations

This feature has no known activations.