INDEX

Explanations

terms related to control policies and regulations, especially in the context of government organizations

oai_token-act-pair · gpt-3.5-turbo

references to governance and regulatory frameworks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

axies

-0.60

STER

-0.60

é¾įåĸļå£«

-0.60

ecast

-0.58

 Wonderful

-0.57

famous

-0.56

akeru

-0.56

 cartoons

-0.56

sonian

-0.55

çīĪ

-0.55

POSITIVE LOGITS

 thresholds

0.71

 impede

0.70

effic

0.69

 ineffective

0.68

 inhib

0.66

 preventing

0.66

 prevents

0.64

 barriers

0.62

CTR

0.61

 exclusion

0.61

Activations Density 1.233%

terms related to control policies and regulations, especially in the context of government organizations

references to governance and regulatory frameworks

No Comments

No Known Activations