INDEX

Explanations

references to the ACT (American College Testing) standardized test and its related metrics

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

words starting with Act and ACT abbreviations

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

EOUT

-0.56

 Riggs

-0.48

erialized

-0.46

providedIn

-0.45

gulp

-0.41

 THROUGH

-0.41

ibid

-0.40

 BROS

-0.40

ira

-0.40

iero

-0.39

POSITIVE LOGITS

ACT

2.14

ACT

1.77

 Acton

0.86

Act

0.81

 Actin

0.81

Actin

0.79

Acta

0.78

ACTED

0.78

Act

0.77

 Acta

0.75

Activations Density 0.013%

references to the ACT (American College Testing) standardized test and its related metrics

words starting with Act and ACT abbreviations

No Comments

No Known Activations