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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

vation

-0.67

aciously

-0.64

allery

-0.63

Reviewer

-0.61

Newsletter

-0.61

ocations

-0.60

croft

-0.60

 parties

-0.60

INAL

-0.59

 satell

-0.59

POSITIVE LOGITS

netflix

0.87

ĸļ

0.82

 McKin

0.76

ainted

0.70

 Calais

0.70

govtrack

0.69

paralle

0.68

 Ridley

0.65

trace

0.65

anmar

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.