INDEX

Explanations

expressions of fear or concern for someone's safety

oai_token-act-pair · gpt-3.5-turbo

expressions of fear for personal safety or well-being

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

•layer 6 - fear

No Comments

Negative Logits

oller

-0.75

BuyableInstoreAndOnline

-0.75

CLE

-0.71

SON

-0.69

ebted

-0.67

edin

-0.67

ãĤ¢ãĥ«

-0.67

YE

-0.67

urat

-0.66

venants

-0.66

POSITIVE LOGITS

gotten

1.27

 example

1.01

 sake

0.99

 instance

0.97

bidden

0.96

 awhile

0.82

 starters

0.80

wards

0.78

geries

0.78

 reasons

0.76

Activations Density 0.119%

expressions of fear or concern for someone's safety

expressions of fear for personal safety or well-being

No Comments

No Known Activations