INDEX

Explanations

specific structured data or metadata markers, particularly in programming or document formats

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

<start_of_turn>user`

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

 resourceCulture

-0.39

Hozzáférés

-0.36

Lastly

-0.35

 mengangg

-0.34

등학교

-0.34

gesehen

-0.33

 Lastly

-0.33

 feste

-0.32

 lên

-0.32

BIND

-0.31

POSITIVE LOGITS

OrNil

0.56

 Infórmanos

0.55

 ſta

0.55

rungsseite

0.54

 للاسماء

0.50

Хьажоргаш

0.50

 uſed

0.50

 Belarusian

0.49

 ſtand

0.49

 myſelf

0.48

Activations Density 0.001%

specific structured data or metadata markers, particularly in programming or document formats

<start_of_turn>user`

No Comments

No Known Activations