INDEX

Explanations

positive affirmations or suggestions

oai_token-act-pair · gpt-3.5-turbo

expressions of positivity and encouragement

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

catentry

-0.68

uscript

-0.66

itsch

-0.64

aru

-0.61

bring

-0.60

 originate

-0.60

Comb

-0.59

¿½

-0.59

ettlement

-0.59

umann

-0.57

POSITIVE LOGITS

OWER

0.68

zee

0.66

 yourselves

0.66

readable

0.66

nn

0.65

 Yourself

0.65

 yourself

0.64

icted

0.64

nown

0.63

 guiName

0.63

Activations Density 0.101%

positive affirmations or suggestions

expressions of positivity and encouragement

No Comments

No Known Activations