INDEX

Explanations

references to drawing or creative artistic activities

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

doodle scribbling

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

 Infórmanos

-0.49



-0.48

 advies

-0.47

 égard

-0.45

SqlClient

-0.44

 heisst

-0.43

 ervaren

-0.43

SqlConnection

-0.42

 tvrd

-0.42

 églises

-0.42

POSITIVE LOGITS

 doodle

1.99

 Doodle

1.92

Doodle

1.91

doodle

1.90

 doodles

1.70

oodles

1.39

 dood

1.35

oodle

1.34

dood

1.16

odles

0.91

Activations Density 0.003%

references to drawing or creative artistic activities

doodle scribbling

No Comments

No Known Activations

references to drawing or creative artistic activities

doodle scribbling

No Comments

No Known Activations