INDEX

Explanations

the word "to" followed by an action or destination

oai_token-act-pair · gpt-3.5-turbo

instances of the phrase "go to" with varying frequencies

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

 thereof

-0.80

 transmitted

-0.69

 contrasted

-0.67

 compounded

-0.66

contained

-0.66

 conveyed

-0.65

tymology

-0.64

auga

-0.64

etheless

-0.62

Released

-0.60

POSITIVE LOGITS

bern

0.79

pless

0.77

bed

0.74

vt

0.73

Ô

0.71

 hell

0.67

ying

0.66

 pick

0.64

 Vegas

0.64

 Mandal

0.64

Activations Density 0.112%

the word "to" followed by an action or destination

instances of the phrase "go to" with varying frequencies

No Comments

No Known Activations