INDEX

Explanations

phrases that express actions related to blame or responsibility

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

repeated references to actions or responsibilities

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

doing things or actions

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

 opportunities

-0.50

Opportunities

-0.48

 Pingback

-0.46

 beslut

-0.46

IsContent

-0.45

 hipó

-0.44

 resources

-0.44

ginfo

-0.44

 presença

-0.43

 Opportunities

-0.43

POSITIVE LOGITS

 thing

0.92

+:+

0.86

 work

0.79

 THING

0.75

 things

0.75

homework

0.73

 deed

0.73

 homework

0.72

job

0.71

 THINGS

0.70

Activations Density 0.097%

phrases that express actions related to blame or responsibility

repeated references to actions or responsibilities

doing things or actions

No Comments

No Known Activations