INDEX

Explanations

references to changes in location or movement

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

movement and location

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

numerusform

-0.36

 Selva

-0.33

council

-0.33

hematical

-0.33

 smug

-0.32

ğunu

-0.31

characters

-0.31

nesota

-0.30

 perus

-0.30

Notae

-0.30

POSITIVE LOGITS

IntoConstraints

0.65

########.

0.58

 relocated

0.57

AnchorStyles

0.51

WebElementEntity

0.50

 위치

0.50

 समीक्षक

0.49

 ioutil

0.48

 relocating

0.48

cèse

0.47

Activations Density 0.057%

references to changes in location or movement

movement and location

No Comments

No Known Activations