INDEX

Explanations

phrases related to making changes or revisions to laws, policies, and systems

oai_token-act-pair · gpt-3.5-turbo

references to changes or revisions in laws and policies

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

vered

-0.73

shi

-0.72

âĹ¼

-0.71

lehem

-0.71

staking

-0.70

ffield

-0.69

aturdays

-0.69

ngth

-0.66

same

-0.65

 paran

-0.65

POSITIVE LOGITS

 regulations

1.05

 outdated

0.94

 wording

0.94

 Regulations

0.94

how

0.92

 existing

0.92

 rules

0.90

 procedures

0.89

 terminology

0.84

 etiquette

0.80

Activations Density 0.184%

phrases related to making changes or revisions to laws, policies, and systems

references to changes or revisions in laws and policies

No Comments

No Known Activations