INDEX

Explanations

projections or possibilities for future outcomes

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

words related to potential future events or outcomes

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

washer

-0.70

orno

-0.69

Maker

-0.68

core

-0.64

furt

-0.64

cloth

-0.64

raining

-0.62

boy

-0.61

val

-0.59

 fashionable

-0.59

POSITIVE LOGITS

 feas

1.15

berra

1.08

 conce

1.05

adian

1.05

be

0.95

 potentially

0.92

 hypot

0.91

 foresee

0.91

 tremend

0.90

 theoretically

0.89

Activations Density 0.085%

projections or possibilities for future outcomes

words related to potential future events or outcomes

No Comments

No Known Activations