INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 Everyday

-0.82

 Brach

-0.79

)).

-0.73

)].

-0.72

 Gibbs

-0.67

 Gund

-0.66

 Tail

-0.65

CK

-0.65

 Hague

-0.64

 Noon

-0.62

POSITIVE LOGITS

itage

0.84

alach

0.76

 mosqu

0.76

 glim

0.75

 barg

0.73

 sprang

0.73

 advoc

0.72

 guid

0.72

 fortun

0.71

 predec

0.71

Activations Density 0.000%

No Known Activations

This feature has no known activations.