INDEX

Explanations

various programming symbols and structure elements

oai_token-act-pair · gpt-4o-mini Triggered by @bot

normal words

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 мәкал

-0.66

GEBURTSDATUM

-0.60

 становника

-0.56

 transfieras

-0.55

رشف

-0.54

 ویکی‌آمباردا

-0.51

 numerus

-0.50

Попис

-0.49

 كومونز

-0.49

 ModelExpression

-0.48

POSITIVE LOGITS

 normal

0.52

normal

0.49

 normale

0.47

 normaux

0.45

 normalen

0.44

Ordinary

0.43

ModelSerializer

0.42

 normales

0.42

Normal

0.41

white

0.41

Activations Density 0.052%

various programming symbols and structure elements

normal words

No Comments

No Known Activations

various programming symbols and structure elements

normal words

No Comments

No Known Activations