INDEX

Explanations

phrases related to actions or events happening or being done 'to' someone or something

oai_token-act-pair · gpt-3.5-turbo

instances of the word "to" indicating purpose or intention

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

typ

-0.60

 disadvant

-0.59

emort

-0.57

 hemor

-0.55

 behav

-0.54

 shenan

-0.54

tun

-0.54

 Seym

-0.53

 vulner

-0.53

 Vaugh

-0.53

POSITIVE LOGITS

ggles

0.83

wered

0.81

ilet

0.77

 celebrate

0.76

 relieve

0.74

 obtain

0.74

 promote

0.73

 accommodate

0.72

asted

0.72

 avoid

0.72

Activations Density 0.199%

phrases related to actions or events happening or being done 'to' someone or something

instances of the word "to" indicating purpose or intention

No Comments

No Known Activations