INDEX

Explanations

single-numbered items in lists

oai_token-act-pair · gpt-3.5-turbo

references to numbered lists or items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

scenes

-0.70

allowed

-0.66

espie

-0.66

leading

-0.65

 fences

-0.64

bent

-0.64

apon

-0.63

awaru

-0.62

 milit

-0.62

thinkable

-0.61

POSITIVE LOGITS

Password

1.29

 Corinthians

1.12

st

1.07

1.06

1.02

Â½

0.95

0.88

0.85

RM

0.80

Activations Density 0.056%

single-numbered items in lists

references to numbered lists or items

No Comments

No Known Activations