INDEX

Explanations

references to speeds, measures, and numerical values related to data or performance

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

Ranges or estimates following "of"

np_acts-logits-general · gemini-2.0-flash

quantities, percentages, and dollar amounts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

RenderAtEndOf

-0.78

RectangleBorder

-0.66

/*

-0.64

 itinéraires

-0.56

autres

-0.55

parian

-0.55

OGND

-0.54

eeper

-0.53

ónde

-0.53

getBoolean

-0.52

POSITIVE LOGITS

 between

0.75

 about

0.73

 approximately

0.70

 just

0.67

 around

0.61

()]);

0.60

between

0.59

 inicialmente

0.56

six

0.56

 five

0.55

Activations Density 0.635%

references to speeds, measures, and numerical values related to data or performance

Ranges or estimates following "of"

quantities, percentages, and dollar amounts

No Comments

No Known Activations