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

uggest

-0.79

ificant

-0.77

swing

-0.73

Ã§a

-0.71

urate

-0.69

otine

-0.67

olean

-0.67

arate

-0.66

ady

-0.66

edIn

-0.66

POSITIVE LOGITS

and

0.75

Au

0.65

ache

0.64

Gi

0.63

Sea

0.62

 Felix

0.62

ARC

0.61

Arc

0.61

 Berks

0.60

 Bucc

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.