INDEX

Explanations

mentions of individuals' names or aliases

oai_token-act-pair · gpt-3.5-turbo

references to individuals named "Abu" in the context of discussions about significant figures or events

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

xual

-0.81

hips

-0.68

ersen

-0.68

intendent

-0.65

mallow

-0.64

iflower

-0.63

 butterfly

-0.63

eries

-0.61

*/(

-0.61

IENCE

-0.61

POSITIVE LOGITS

 Dhabi

1.66

 Bakr

1.45

hammad

1.14

rahim

0.96

Ali

0.94

Haf

0.93

jah

0.92

ja

0.91

ghan

0.88

 Muhammad

0.88

Activations Density 0.023%

mentions of individuals' names or aliases

references to individuals named "Abu" in the context of discussions about significant figures or events

No Comments

No Known Activations