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

-0.59

sound

-0.57

byte

-0.57

 msec

-0.57

URL

-0.57

enced

-0.55

bc

-0.55

mn

-0.54

 themselves

-0.54

codes

-0.54

POSITIVE LOGITS

rift

0.86

opian

0.81

 Imperium

0.81

omaly

0.74

hemy

0.73

unda

0.73

icz

0.71

 Scourge

0.70

ifice

0.70

enburg

0.69

Activations Density 0.000%

No Known Activations

This feature has no known activations.