INDEX

Explanations

calls to action encouraging the reader to engage with a book or content

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

Follows punctuation or parentheses

np_acts-logits-general · gemini-2.0-flash

immediately after punctuation

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

脚注の使い方

-0.53

ContentLoaded

-0.51

<bos>

-0.50

Numerology

-0.48

ServletConfig

-0.47

données

-0.46

pport

-0.46

 chande

-0.46

 dealt

-0.45



-0.44

POSITIVE LOGITS

早速

0.80

さっそく

0.78

 henceforth

0.72

migrationBuilder

0.67

 forthwith

0.66

 immediately

0.59

今度

0.59

 next

0.59

 теперь

0.58

immediately

0.57

Activations Density 0.229%

calls to action encouraging the reader to engage with a book or content

Follows punctuation or parentheses

immediately after punctuation

No Comments

No Known Activations