INDEX

Explanations

phrases expressing positive value judgments or satisfaction

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

evaluating things

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

 före

-0.32

 entraîner

-0.31

 Gubernur

-0.31

 graduación

-0.30

 montañas

-0.30

 kuulu

-0.29

 уста

-0.28

')")

-0.28

Concerns

-0.28

Дереккөздер

-0.28

POSITIVE LOGITS

 propOrder

0.79

IntoConstraints

0.71

featureID

0.64

 ModelExpression

0.63

 ویکی‌پدیا

0.60

ContentLoaded

0.57

 decent

0.56

 непло

0.55

Decent

0.55

RotationOrder

0.54

Activations Density 0.162%

phrases expressing positive value judgments or satisfaction

evaluating things

No Comments

No Known Activations

phrases expressing positive value judgments or satisfaction

evaluating things

No Comments

No Known Activations