INDEX

Explanations

significant numerical data or values within a text

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

code and programming constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

AddTagHelper

-0.77

IUrlHelper

-0.69

transQ

-0.68

 surla

-0.61

 ExecuteAsync

-0.59

期刊论文

-0.57

ReusableCell

-0.57

✨:

-0.57

writeFieldEnd

-0.55

يكب

-0.55

POSITIVE LOGITS

mappedBy

0.33

ffffffff

0.29

ніципа

0.29

 onOptions

0.29

 ulei

0.27

vý

0.27

orElse

0.27

 chi̍t

0.27

EndGlobalSection

0.27

 diatur

0.27

Activations Density 0.000%

significant numerical data or values within a text

code and programming constructs

No Comments

No Known Activations