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

sheets

-0.77

cob

-0.71

SIGN

-0.69

"},"

-0.64

Translation

-0.62

Documents

-0.61

heid

-0.61

ecause

-0.61

Minecraft

-0.61

 quotas

-0.60

POSITIVE LOGITS

 wearer

0.74

icrobial

0.73

eness

0.72

 Savage

0.68

etts

0.68

antha

0.64

 utility

0.64

gres

0.63

ifact

0.62

ett

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.