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

 ILCS

-0.81

 Fitz

-0.78

tein

-0.73

 Railroad

-0.73

icut

-0.70

 Audrey

-0.67

 liner

-0.66

 Toll

-0.64

 Hudson

-0.64

 Lazarus

-0.64

POSITIVE LOGITS

doms

0.78

against

0.73

elist

0.72

zes

0.70

xual

0.69

worthiness

0.67

pmwiki

0.67

binary

0.67

defense

0.66

WARE

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.