INDEX

Explanations

phrases related to strict adherence or enforcement of rules, guidelines, or conditions

oai_token-act-pair · gpt-3.5-turbo

phrases indicating strictness or adherence to rules

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

lain

-0.84

 Tycoon

-0.84

ocene

-0.72

ilater

-0.72

PokÃ©mon

-0.69

 Healing

-0.69

ulton

-0.68

okemon

-0.67

igate

-0.66

assies

-0.65

POSITIVE LOGITS

 prohibited

0.99

 minded

0.94

 exempted

0.92

 enforced

0.87

tics

0.86

 exempt

0.84

 adherent

0.84

 speaking

0.83

 adhere

0.82

 obliged

0.81

Activations Density 0.004%

phrases related to strict adherence or enforcement of rules, guidelines, or conditions

phrases indicating strictness or adherence to rules

No Comments

No Known Activations