INDEX

Explanations

words that express emphasis or degree

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

Cyfeiriadau

-0.77

 Sahara

-0.68

XtraEditors

-0.58

ίος

-0.58

ΙΑ

-0.56

JAXB

-0.56

__;

-0.55

NBS

-0.55

 Valera

-0.55

ADM

-0.54

POSITIVE LOGITS

 &___

0.69

icating

0.68

nsic

0.63

 foule

0.60

 fewer

0.60

Frat

0.60

 yalnızca

0.60

NameInMap

0.59

tifying

0.59

 Sebab

0.59

Activations Density 0.090%

words that express emphasis or degree

No Comments

No Known Activations