INDEX

Explanations

food and drink items

oai_token-act-pair · gpt-3.5-turbo

terms and phrases related to food and pricing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 appealing

-0.54

swing

-0.52

paio

-0.51

 tempting

-0.51

 recall

-0.50

 mend

-0.49

 overt

-0.49

 desirable

-0.48

 camp

-0.48

 unfavorable

-0.46

POSITIVE LOGITS

(@

0.64

ocre

0.64

eday

0.63

_.

0.61

sic

0.61

_-

0.59

ONSORED

0.59

?,

0.58

_(

0.57

Laughs

0.56

Activations Density 0.975%

food and drink items

terms and phrases related to food and pricing

No Comments

No Known Activations