INDEX

Explanations

terms or phrases that indicate significance or relevance in various contexts, particularly legal, procedural, and analytical situations

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

isSuccessful

-0.49

RLock

-0.48

Honours

-0.48

 NSCoder

-0.47

ссора

-0.47

 vagy

-0.45

nthetic

-0.45

or

-0.44

än

-0.44

 jamais

-0.43

POSITIVE LOGITS

 related

0.84

 متعلقه

0.82

 corresponding

0.81

Related

0.79

 relevant

0.78

 المعيارى

0.77

 appropriate

0.74

 thereto

0.74

 associated

0.73

 entsprechende

0.73

Activations Density 0.586%

terms or phrases that indicate significance or relevance in various contexts, particularly legal, procedural, and analytical situations

No Comments

No Known Activations