INDEX

Explanations

verbs indicating strong emotions or personal perspectives

oai_token-act-pair · gpt-3.5-turbo

forms of the verb "to be" in various tenses

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

 Previous

-0.54

inav

-0.54

atives

-0.53

 Which

-0.51

 Benefits

-0.51

stop

-0.51

urry

-0.49

 IMAGES

-0.49

 Moines

-0.48

osate

-0.47

POSITIVE LOGITS

nt

0.89

 supposed

0.83

 definitely

0.78

senal

0.77

not

0.73

 indeed

0.72

 unlikely

0.71

rael

0.71

 always

0.71

 able

0.71

Activations Density 0.830%

verbs indicating strong emotions or personal perspectives

forms of the verb "to be" in various tenses

No Comments

No Known Activations