INDEX

Explanations

mentions of police incidents and emergency situations

oai_token-act-pair · gpt-3.5-turbo

references to police activity and emergency response incidents

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

Tokens

-0.90

rylic

-0.74

hiba

-0.72

 glide

-0.71

eday

-0.70

 sacrific

-0.69

 rubbed

-0.69

 folds

-0.68

 compares

-0.68

 grind

-0.67

POSITIVE LOGITS

 disturbance

0.95

 disturbances

0.89

 suspicious

0.85

 suspected

0.85

 Incident

0.84

 suspicion

0.84

 suspicions

0.84

 emergency

0.83

 incidents

0.83

 burglary

0.83

Activations Density 0.369%

mentions of police incidents and emergency situations

references to police activity and emergency response incidents

No Comments

No Known Activations