INDEX

Explanations

locations and violent incidents

oai_token-act-pair · gpt-3.5-turbo

references to incidents of violence or emergency situations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

onom

-0.67

rogram

-0.67

ONEY

-0.65

 substit

-0.65

 matured

-0.62

 guiding

-0.61

 legends

-0.61

 evolves

-0.60

erity

-0.60

 Sanskrit

-0.60

POSITIVE LOGITS

 suburb

0.87

 premises

0.83

 intersection

0.81

 precinct

0.79

 Plaza

0.79

 precincts

0.77

 nightclub

0.76

 bloc

0.75

area

0.75

 gunfire

0.75

Activations Density 0.539%

locations and violent incidents

references to incidents of violence or emergency situations

No Comments

No Known Activations