INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

zinski

-0.86

 Organization

-0.79

ogy

-0.71

Der

-0.70

SourceFile

-0.67

iger

-0.66

 Organisation

-0.65

ãĤ¡

-0.65

ħĭ

-0.64

ogle

-0.63

POSITIVE LOGITS

iage

0.81

srf

0.67

 sinners

0.65

 mosqu

0.64

insula

0.62

 toget

0.61

 Trib

0.61

ensibly

0.61

 offenders

0.61

haps

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.