INDEX

Explanations

elements related to data structure definitions and schemas

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

enamor, sindre, comment_only

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

 ſind

-0.65

 arşivlendi

-0.62

ⵌ

-0.54

kari

-0.53

 erſt

-0.53

IndentedString

-0.52

нгред

-0.52

 kaarangay

-0.52

 indígen

-0.52

 kapture

-0.51

POSITIVE LOGITS

 innamor

0.39

 enamor

0.38

 enamorado

0.35

 grunn

0.34

område

0.33

RemoveField

0.33

 typically

0.32

 explicado

0.32

 desac

0.31

 invokingState

0.31

Activations Density 0.006%

elements related to data structure definitions and schemas

enamor, sindre, comment_only

No Comments

No Known Activations

elements related to data structure definitions and schemas

enamor, sindre, comment_only

No Comments

No Known Activations