INDEX

Explanations

references to specific items or concepts within a document

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

Sentences starting with "This" or "this"

np_acts-logits-general · gemini-2.0-flash

this is followed by subsequent info

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

dr

-0.48

 répé

-0.43

dr

-0.42

RequestBuilder

-0.42

例句

-0.42

Sta

-0.41

 toujours

-0.40

anın

-0.39

 goû

-0.38

 subset

-0.37

POSITIVE LOGITS

StoryboardSegue

0.90

RenderAtEndOf

0.89

 متعلقه

0.88

QMetaType

0.79

 مشين

0.79

 تضيفلها

0.79

reportWebVitals

0.76

jsxFileName

0.73

 shenan

0.71

 purpoſe

0.69

Activations Density 0.227%

references to specific items or concepts within a document

Sentences starting with "This" or "this"

this is followed by subsequent info

No Comments

No Known Activations