INDEX

Explanations

prohibitions or restrictions set by rules or regulations

oai_token-act-pair · gpt-3.5-turbo

terms related to prohibition or restrictions

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

eah

-0.84

prise

-0.78

sonian

-0.75

ensional

-0.74

eon

-0.72

gener

-0.72

ctl

-0.72

ipel

-0.70

lings

-0.70

bench

-0.70

POSITIVE LOGITS

 prohibited

0.96

 prohibits

0.83

 forbids

0.83

 violations

0.81

etheless

0.79

 prohibition

0.79

bidden

0.79

avorite

0.78

 prohibit

0.78

 forbidden

0.76

Activations Density 0.029%

prohibitions or restrictions set by rules or regulations

terms related to prohibition or restrictions

No Comments

No Known Activations