INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

cker

-0.75

ouf

-0.70

ogle

-0.70

NB

-0.69

ottenham

-0.68

uci

-0.68

omsky

-0.68

maxwell

-0.67

ococ

-0.66

abi

-0.65

POSITIVE LOGITS

iments

0.68

 dissolve

0.67

itudinal

0.65

 kinds

0.64

imental

0.63

iment

0.63

Õ

0.62

Ú

0.62

matic

0.61

fam

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.