INDEX

Explanations

phrases related to critical medical conditions

oai_token-act-pair · gpt-3.5-turbo

references to individuals in critical condition or serious health situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

endas

-0.56

Reviewer

-0.54

 Solitaire

-0.52

 Genocide

-0.51

ModLoader

-0.49

 Empires

-0.49

 Chains

-0.49

 Medals

-0.49

 virginity

-0.48

indal

-0.48

POSITIVE LOGITS

ina

0.53

line

0.52

based

0.52

lled

0.52

ling

0.51

led

0.51

typically

0.51

uh

0.50

backed

0.50

ciplinary

0.49

Activations Density 0.600%

phrases related to critical medical conditions

references to individuals in critical condition or serious health situations

No Comments

No Known Activations