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

emort

-0.79

erion

-0.76

rate

-0.71

Plugin

-0.70

Pers

-0.70

Notice

-0.68

ieu

-0.67

Render

-0.67

PDATE

-0.66

itect

-0.66

POSITIVE LOGITS

"},{"

0.75

"}],"

0.73

enegger

0.73

Edu

0.70

verning

0.69

 constitu

0.66

 Lans

0.65

 Franch

0.64

erves

0.63

 Shirley

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.