INDEX

Explanations

the word "one"

oai_token-act-pair · gpt-3.5-turbo

references to singular instances or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ulner

-0.68

folk

-0.68

ooks

-0.67

inders

-0.66

lain

-0.66

emies

-0.66

older

-0.65

Leaks

-0.63

hips

-0.63

ypes

-0.62

POSITIVE LOGITS

 hundred

0.92

 Piece

0.78

 sided

0.76

 Hundred

0.75

 particular

0.72

 playthrough

0.71

IDA

0.71

 hour

0.70

 million

0.69

 minute

0.68

Activations Density 0.057%

the word "one"

references to singular instances or concepts

No Comments

No Known Activations