INDEX

Explanations

phrases related to rules, regulations, or strict adherence to protocols

oai_token-act-pair · gpt-3.5-turbo

statements that emphasize strictness or absoluteness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 Tycoon

-0.76

lain

-0.73

ilater

-0.69

 Samoa

-0.68

 Cards

-0.67

assies

-0.66

ulton

-0.66

 Eggs

-0.66

akeru

-0.65

 Healing

-0.64

POSITIVE LOGITS

 prohibited

0.96

 minded

0.94

wcsstore

0.89

tics

0.85

 exempted

0.85

 enforced

0.82

 speaking

0.80

 restricted

0.79

 regulated

0.78

 confined

0.78

Activations Density 0.010%

phrases related to rules, regulations, or strict adherence to protocols

statements that emphasize strictness or absoluteness

No Comments

No Known Activations