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

 Upton

-0.79

 Died

-0.71

 Begins

-0.68

ãĥŁ

-0.67

 Chapman

-0.65

 Bett

-0.64

 Tests

-0.62

Ran

-0.61

 Apply

-0.60

advertising

-0.58

POSITIVE LOGITS

isine

0.84

£ı

0.78

ĸļ

0.77

typ

0.73

«ĺ

0.73

rency

0.71

raphic

0.68

umper

0.68

ophone

0.67

iffe

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.