INDEX

Explanations

locations and events related to warfare and conflict

oai_token-act-pair · gpt-3.5-turbo

geographical locations and names related to conflict zones

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

 CEOs

-0.66

 crank

-0.63

SJ

-0.62

 promoters

-0.60

 detectives

-0.60

neo

-0.60

CEO

-0.60

 pitchers

-0.60

 railing

-0.60

 narciss

-0.59

POSITIVE LOGITS

qqa

1.16

arah

1.05

amiya

1.00

bil

0.99

raq

0.98

abul

0.98

area

0.95

iyah

0.93

ujah

0.93

myra

0.92

Activations Density 0.127%

locations and events related to warfare and conflict

geographical locations and names related to conflict zones

No Comments

No Known Activations