INDEX

Explanations

questions or statements involving people's thoughts, actions, or inquiries

oai_token-act-pair · gpt-3.5-turbo

phrases related to people's behaviors and interactions

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

quished

-0.81

 teasp

-0.69

 srfAttach

-0.69

rontal

-0.66

poral

-0.66

 overseen

-0.64

 presided

-0.63

VIDIA

-0.62

 executive

-0.61

Cu

-0.60

POSITIVE LOGITS

 themselves

0.88

 alike

0.81

 theirs

0.78

inge

0.71

 THEIR

0.69

their

0.69

 clam

0.69

selves

0.67

sense

0.67

 their

0.67

Activations Density 0.484%

questions or statements involving people's thoughts, actions, or inquiries

phrases related to people's behaviors and interactions

No Comments

No Known Activations