INDEX

Explanations

expressions of opinion or reviews, particularly positive commentary

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

Punctuation followed by a capitalized word

np_acts-logits-general · gemini-2.0-flash

store values

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

expandindo

-0.74

一応

-0.71

)();

-0.67

EndGlobalSection

-0.65

mybatisplus

-0.65

Diweddarwch

-0.63

laise

-0.62

 هيا

-0.60

 GeoNames

-0.60

VYMaps

-0.59

POSITIVE LOGITS

Watching

0.66

 always

0.64

 Watching

0.64

 nothing

0.63

 Rarely

0.62

 often

0.61

 whenever

0.61

Whenever

0.61

 Truly

0.60

 watching

0.60

Activations Density 0.160%

expressions of opinion or reviews, particularly positive commentary

Punctuation followed by a capitalized word

store values

No Comments

No Known Activations