INDEX

Explanations

mentions of the word "groovy."

oai_token-act-pair · gpt-3.5-turbo

references to the term "groovy" and its variations as well as currency-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 shade

-0.74

 scor

-0.63

 Vietnamese

-0.63

 meaning

-0.62

 jeopardy

-0.61

<<

-0.60

 spanning

-0.60

 misc

-0.60

IENT

-0.59

 complexity

-0.59

POSITIVE LOGITS

ovy

1.69

deen

0.98

doms

0.87

Zup

0.80

udeb

0.77

Lago

0.75

Brit

0.74

eday

0.74

glomer

0.73

ortment

0.73

Activations Density 0.006%

mentions of the word "groovy."

references to the term "groovy" and its variations as well as currency-related terms

No Comments

No Known Activations