INDEX

Explanations

punctuation marks and syntax-related tokens

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

finding by id

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

出版年

-0.61

httphttps

-0.57

 Infórmanos

-0.56

addCriterion

-0.52

########.

-0.52

 surla

-0.52

 informée

-0.51

 &___

-0.50

 utafitiHapana

-0.50

oa̍t

-0.48

POSITIVE LOGITS

 findById

0.60

findById

0.55

ById

0.54

ByPrimaryKey

0.50

 detail

0.48

select

0.46

getElementById

0.46

detail

0.45

ByID

0.45

 getById

0.45

Activations Density 0.004%

punctuation marks and syntax-related tokens

finding by id

No Comments

No Known Activations