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

 Cere

-0.75

 millisec

-0.70

 Typh

-0.68

odder

-0.68

 cere

-0.68

 dexter

-0.66

bru

-0.64

 Cable

-0.63

bidden

-0.62

 indo

-0.62

POSITIVE LOGITS

apo

0.87

ANA

0.78

stock

0.72

oir

0.70

stanbul

0.69

================================================================

0.69

iors

0.68

VID

0.66

historic

0.66

SHARE

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.