INDEX

Explanations

questions or statements starting with "Who is" or "Who's", indicating a focus on identifying or questioning specific individuals or entities

oai_token-act-pair · gpt-3.5-turbo

questions related to the identity and actions of individuals

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

avascript

-0.86

nothing

-0.74

irth

-0.63

tesque

-0.63

ooters

-0.62

actory

-0.62

urances

-0.62

olson

-0.61

erald

-0.60

Nothing

-0.60

POSITIVE LOGITS

 whom

1.01

 footing

0.92

 responsible

0.91

 benefiting

0.83

responsible

0.78

 accountable

0.76

 benef

0.73

liest

0.73

 smartest

0.72

 tallest

0.72

Activations Density 0.110%

questions or statements starting with "Who is" or "Who's", indicating a focus on identifying or questioning specific individuals or entities

questions related to the identity and actions of individuals

No Comments

No Known Activations