INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ONSORED

-0.87

mens

-0.82

ovember

-0.73

henko

-0.72

 Guerrero

-0.69

querque

-0.69

edom

-0.69

irez

-0.69

onto

-0.68

eper

-0.67

POSITIVE LOGITS

 Canon

0.71

 Hide

0.68

finder

0.66

ames

0.65

olkien

0.62

Narr

0.61

paren

0.59

 navig

0.57

 Photograph

0.57

 loader

0.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.