INDEX

Explanations

words related to medical conditions, particularly strokes

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "stroke" and its variations, indicating a focus on medical events or conditions related to strokes

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

%"

-0.73

guyen

-0.72

gemony

-0.68

itive

-0.67

etheless

-0.67

ãĤ©

-0.66

gart

-0.64

essor

-0.63

rum

-0.62

 starch

-0.61

POSITIVE LOGITS

 stroke

1.03

manship

0.95

 strokes

0.88

stroke

0.72

weed

0.70

 Stro

0.70

aukee

0.68

stem

0.63

teenth

0.61

zzi

0.61

Activations Density 0.023%

words related to medical conditions, particularly strokes

occurrences of the word "stroke" and its variations, indicating a focus on medical events or conditions related to strokes

No Comments

No Known Activations