INDEX

Explanations

nouns and actions related to characters and their interactions in a narrative context

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

physical actions

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

SBATCH

-0.48

Билгалдахарш

-0.48

AndEndTag

-0.47

findpost

-0.44

ConstraintMaker

-0.44

demment

-0.43

Населення

-0.43

 jsPsych

-0.43

 endroit

-0.42

 Schengen

-0.42

POSITIVE LOGITS

writeField

0.52

 jspb

0.48

 suitcases

0.45

 disarm

0.44

 tears

0.44

ItemBackground

0.42

 rooftop

0.42

 Coff

0.41

 Rooftop

0.41

 clap

0.40

Activations Density 0.062%

nouns and actions related to characters and their interactions in a narrative context

physical actions

No Comments

No Known Activations