INDEX

Explanations

terms related to web development and coding, particularly focusing on HTML and CSS elements

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

rontal

-0.89

ceed

-0.73

sburgh

-0.71

ilitation

-0.70

vertising

-0.65

lishing

-0.63

milo

-0.62

 Gamble

-0.61

sic

-0.61

creen

-0.61

POSITIVE LOGITS

alogy

0.88

ARY

0.86

ById

0.86

arium

0.83

als

0.80

agen

0.79

icide

0.77

 abund

0.76

abeth

0.75

abetic

0.74

Activations Density 0.022%

terms related to web development and coding, particularly focusing on HTML and CSS elements

No Comments

No Known Activations