INDEX

Explanations

uses of the word "highlight" related to emphasizing, pointing out or showcasing information or issues

oai_token-act-pair · gpt-3.5-turbo

references to highlighting important information or features

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

cas

-0.77

itte

-0.75

thood

-0.71

hell

-0.69

ja

-0.68

onew

-0.66

nery

-0.65

cill

-0.64

soever

-0.64

ni

-0.63

POSITIVE LOGITS

 reel

0.92

 highlights

0.85

ibilities

0.80

ibility

0.79

Marginal

0.71

 warnings

0.71

 milestones

0.71

 highlighting

0.70

OWS

0.70

umenthal

0.70

Activations Density 0.049%

uses of the word "highlight" related to emphasizing, pointing out or showcasing information or issues

references to highlighting important information or features

No Comments

No Known Activations