INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

Reloaded

-0.77

ONSORED

-0.72

ERG

-0.65

UES

-0.64

osure

-0.62

isms

-0.62

chu

-0.61

 rejection

-0.60

["

-0.59

Connection

-0.59

POSITIVE LOGITS

 guiActiveUn

0.81

apo

0.79

çīĪ

0.78

 eleph

0.77

ibel

0.76

aned

0.75

 sidx

0.74

zik

0.70

emort

0.68

 framed

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.