INDEX

Explanations

terms related to rules, regulations, and compliance

oai_token-act-pair · gpt-3.5-turbo

references to regulations and compliance standards

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 istg

-0.82

orescence

-0.77

iris

-0.76

enaries

-0.75

vous

-0.75

naissance

-0.72

ertodd

-0.70

ppel

-0.68

uilding

-0.68

ocamp

-0.67

POSITIVE LOGITS

 rules

1.94

 guidelines

1.83

 norms

1.79

 regulations

1.78

 standards

1.77

rules

1.64

 laws

1.63

 rule

1.60

 Rules

1.51

 etiquette

1.49

Activations Density 0.909%

terms related to rules, regulations, and compliance

references to regulations and compliance standards

No Comments

No Known Activations