INDEX

Explanations

specific mentions of entities (e.g., organizations, locations, individuals)

oai_token-act-pair · gpt-3.5-turbo

phrases referencing law enforcement or legal actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

opsis

-0.78

 preceded

-0.77

worn

-0.76

 followed

-0.69

auntlet

-0.67

ingen

-0.66

arrow

-0.65

pread

-0.65

 namely

-0.64

çĭ

-0.64

POSITIVE LOGITS

 Ministry

1.23

 Department

1.16

 feds

1.12

 Office

1.01

 Bureau

1.01

 ACLU

0.99

 manufacturer

0.99

 Centers

0.99

 Dept

0.98

FBI

0.97

Activations Density 0.399%

specific mentions of entities (e.g., organizations, locations, individuals)

phrases referencing law enforcement or legal actions

No Comments

No Known Activations