INDEX

Explanations

mentions of people being physically injured

oai_token-act-pair · gpt-3.5-turbo

mentions of injuries in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

SpaceEngineers

-0.77

tz

-0.72

ularity

-0.70

perm

-0.68

gency

-0.65

etics

-0.65

graph

-0.64

AMA

-0.64

hist

-0.63

 snipp

-0.62

POSITIVE LOGITS

jured

0.85

 bystanders

0.81

 Survivors

0.73

 wounding

0.72

 sustained

0.71

../

0.70

mond

0.69

 injuring

0.68

nikov

0.68

monton

0.66

Activations Density 0.038%

mentions of people being physically injured

mentions of injuries in various contexts

No Comments

No Known Activations