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

iewicz

-0.85

icter

-0.84

ilon

-0.76

orsche

-0.72

icio

-0.71

ADVERTISEMENT

-0.70

itsch

-0.70

isites

-0.69

awei

-0.68

odder

-0.68

POSITIVE LOGITS

stairs

0.80

bra

0.72

boards

0.68

eye

0.65

 Warwick

0.65

bi

0.63

rir

0.63

 irrig

0.62

league

0.62

Rated

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.