INDEX

Explanations

words related to future outcomes or events

oai_token-act-pair · gpt-3.5-turbo

references to outcomes or consequences

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

books

-0.80

book

-0.74

PAC

-0.72

BOOK

-0.68

 anecd

-0.66

gun

-0.66

guns

-0.66

emen

-0.64

toe

-0.63

lua

-0.63

POSITIVE LOGITS

ity

1.21

ities

1.11

ITY

1.00

 demise

0.94

aneously

0.89

 winner

0.85

 occupant

0.83

 downfall

0.83

itous

0.81

 bankruptcy

0.80

Activations Density 0.020%

words related to future outcomes or events

references to outcomes or consequences

No Comments

No Known Activations