INDEX

Explanations

negative sentiments and assessments related to experiences or conditions

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

loss leader at best

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

DockStyle

-0.79

脚注の使い方

-0.71

 initComponents

-0.65

ChildScrollView

-0.61

出版年

-0.59

Portale

-0.56

MessageState

-0.55

 كومونز

-0.54

Jîn

-0.53

genicity

-0.52

POSITIVE LOGITS

/*

0.36

tidaknya

0.35

 tumbuhan

0.33

 OMITBAD

0.33

 занимается

0.32

 violate

0.32

#!/

0.32

0.31

//

0.31

<!

0.31

Activations Density 0.063%

negative sentiments and assessments related to experiences or conditions

loss leader at best

No Comments

No Known Activations