INDEX

Explanations

mentions of "point" in various contexts, often related to data, references, or discussions

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

"point" followed by various prepositions

np_acts-logits-general · gemini-2.0-flash

point treatment or specific instances

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-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

expandindo

-0.76

<?

-0.72

errHandler

-0.71

 HasFactory

-0.70

AndroidJUnit

-0.70

CORBA

-0.69

OGND

-0.66

 snippetHide

-0.66

AddHtmlAttribute

-0.65

apimachinery

-0.64

POSITIVE LOGITS

 Loma

0.65

Points

0.61

lessly

0.61

 POINT

0.59

blank

0.58

 Point

0.57

 culmin

0.57

 Points

0.56

points

0.56

 fact

0.54

Activations Density 0.199%

mentions of "point" in various contexts, often related to data, references, or discussions

"point" followed by various prepositions

point treatment or specific instances

No Comments

No Known Activations