INDEX

Explanations

instances of police encounters or car stops

oai_token-act-pair · gpt-3.5-turbo

instances of the word "stopped" related to traffic stops or police interactions

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

Not in Any Lists

No Comments

Negative Logits

natureconservancy

-1.03

wcs

-1.02

rina

-0.75

BIT

-0.74

emic

-0.71

idia

-0.70

ergic

-0.69

nia

-0.68

uther

-0.66

yss

-0.66

POSITIVE LOGITS

 compr

0.80

 parked

0.78

 Santana

0.76

 motorcycles

0.75

OTA

0.71

 robbery

0.69

 parking

0.68

 cars

0.68

 Fargo

0.68

rob

0.67

Activations Density 0.077%

instances of police encounters or car stops

instances of the word "stopped" related to traffic stops or police interactions

No Comments

No Known Activations