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

 ILCS

-0.87

xual

-0.86

 Reloaded

-0.78

sembly

-0.78

udeau

-0.77

xus

-0.76

 chamber

-0.76

enhagen

-0.72

icka

-0.69

 unfocusedRange

-0.67

POSITIVE LOGITS

IPM

0.88

igi

0.87

gm

0.62

Flag

0.61

sic

0.60

rag

0.60

RP

0.59

luent

0.59

).[

0.57

rud

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.