INDEX

Explanations

phrases or words that are emphasized or brought to attention

oai_token-act-pair · gpt-3.5-turbo

instances of the word "highlight" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

thood

-0.77

ja

-0.75

itte

-0.74

onz

-0.71

hell

-0.71

mia

-0.70

ilk

-0.66

iott

-0.66

onew

-0.65

cery

-0.64

POSITIVE LOGITS

 weaknesses

0.92

 reel

0.91

 similarities

0.89

 shortcomings

0.89

 highlights

0.87

 differences

0.87

 inconsistencies

0.85

 accomplishments

0.84

 deficiencies

0.83

 flaws

0.83

Activations Density 0.079%

phrases or words that are emphasized or brought to attention

instances of the word "highlight" and its variations

No Comments

No Known Activations