INDEX

Explanations

imperative and suggestion phrases aimed at guiding actions

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

can followed by verb

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

ロウィン

-0.77

tagHelperRunner

-0.76

 NSCoder

-0.75

ſelben

-0.75

tvguidetime

-0.73

 wiſſen

-0.73

 ſehen

-0.70

AddTagHelper

-0.68

ſicht

-0.68

 ſeyn

-0.68

POSITIVE LOGITS

 ceinture

0.37

 TAMBIÉN

0.28

Werke

0.27

 Thank

0.27

DoubleQuotes

0.27

 cuisson

0.26

 uñas

0.26

False

0.26

 fallas

0.26

 False

0.25

Activations Density 0.001%

imperative and suggestion phrases aimed at guiding actions

can followed by verb

No Comments

No Known Activations