INDEX

Explanations

technical terms and notation commonly found in scientific or programming contexts

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

Code snippets/file names with extensions

np_acts-logits-general · gemini-2.0-flash

click here

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 виправивши

-0.65

WebElementEntity

-0.58

 EconPapers

-0.57

exitRule

-0.56

싶

-0.55

WindowConstants

-0.53

 namelijk

-0.52

 azar

-0.52

 ujednoznacz

-0.52

 blumen

-0.51

POSITIVE LOGITS

bitField

0.87

 سكانية

0.76

HtmlAttribute

0.74

例文帳に追加

0.72

verifyException

0.67

awtextra

0.66

<!--[

0.66

rrggbb

0.64

 unknownFields

0.61

endphp

0.61

Activations Density 0.488%

technical terms and notation commonly found in scientific or programming contexts

Code snippets/file names with extensions

click here

No Comments

No Known Activations