INDEX

Explanations

phrases related to violations of rules or laws

oai_token-act-pair · gpt-3.5-turbo

references to legal violations and rights

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

acs

-0.88

onna

-0.80

vale

-0.76

borgh

-0.76

uilding

-0.74

ussen

-0.73

isSpecialOrderable

-0.72

 dwind

-0.71

nis

-0.71

ington

-0.70

POSITIVE LOGITS

Ö¼

0.90

ł

0.75

 contractual

0.75

Third

0.75

 norms

0.73

 jurisdiction

0.73

 confidentiality

0.72

ĺħ

0.72

 principle

0.71

 precedent

0.71

Activations Density 0.124%

phrases related to violations of rules or laws

references to legal violations and rights

No Comments

No Known Activations