INDEX

Explanations

references to mathematical terminology and concepts

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

Code diffs or mathematical tables

np_acts-logits-general · gemini-2.0-flash

technical markdown and code excerpts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

GEBURTSDATUM

-0.82

 CallOverrides

-0.62

@"/

-0.55

LookAnd

-0.54

页

-0.53

Unmarshaller

-0.52

 colpa

-0.52

OGND

-0.52

ĝo

-0.51

Zeneca

-0.51

POSITIVE LOGITS

 InputDecoration

0.71

localctx

0.69

0.68

 snippetHide

0.64

TintMode

0.63

errHandler

0.58

 '\\;'

0.58

APORE

0.56

PreInfinity

0.56

<blockquote>

0.55

Activations Density 0.218%

references to mathematical terminology and concepts

Code diffs or mathematical tables

technical markdown and code excerpts

No Comments

No Known Activations