INDEX

Explanations

phrases indicating that something is not related or relevant to a particular topic

oai_token-act-pair · gpt-3.5-turbo

phrases asserting the irrelevance or disconnection of topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

©¶æ¥µ

-0.84

umerous

-0.78

earchers

-0.77

aughters

-0.75

estyles

-0.72

endiary

-0.71

enza

-0.70

 teasp

-0.70

sites

-0.70

ccording

-0.70

POSITIVE LOGITS

 ours

1.34

 yours

1.31

us

1.27

 reality

1.27

me

1.19

 theirs

1.18

 humanity

1.16

 itself

1.09

 feminism

1.02

 hers

1.00

Activations Density 0.336%

phrases indicating that something is not related or relevant to a particular topic

phrases asserting the irrelevance or disconnection of topics

No Comments

No Known Activations