INDEX

Explanations

characters and symbols used in titles or subtitles

oai_token-act-pair · gpt-3.5-turbo

references to specific statistics or structured data within a context

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 shred

-0.71

 forgetting

-0.70

 envy

-0.69

 civilisation

-0.69

 identifiable

-0.68

 litter

-0.67

 implant

-0.67

 clutter

-0.66

 blinding

-0.66

venge

-0.65

POSITIVE LOGITS

MEN

0.99

 GOODMAN

0.96

ENG

0.92

ANS

0.91

POL

0.88

VIEW

0.88

 Protesters

0.86

GROUND

0.85

 VIDE

0.84

 Editors

0.83

Activations Density 0.223%

characters and symbols used in titles or subtitles

references to specific statistics or structured data within a context

No Comments

No Known Activations