INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

shy

-0.70

 hell

-0.65

«ĺ

-0.65

²

-0.63

GIF

-0.63

 garn

-0.62

 curve

-0.62

ahoo

-0.61

 whim

-0.60

 decor

-0.60

POSITIVE LOGITS

airs

0.80

Ott

0.75

Introduced

0.71

 isot

0.70

Manufact

0.69

kered

0.68

acus

0.68

acet

0.68

Ä

0.68

boats

0.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.