INDEX

Explanations

references to possessive pronouns and related terms

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 himself

-0.66

 oneself

-0.64

 themselves

-0.63

AxisAlignment

-0.61

denly

-0.60

 sendiri

-0.60

 Himself

-0.60

herself

-0.58

ksikon

-0.57

 herself

-0.57

POSITIVE LOGITS

hésitez

0.57

 विश्वसनीयता

0.54

adaptiveStyles

0.50

StreetMap

0.49

 ModelExpression

0.48

begingroup

0.47

tênis

0.47

printStats

0.47

opsida

0.47

 possam

0.47

Activations Density 0.105%

references to possessive pronouns and related terms

No Comments

No Known Activations