INDEX

Explanations

references to sections and summaries within a text

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

LetWeTheoremAssume

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

markers of discourse structure — section headers, transitions and summary phrases (e.g., "We now summarize", "The", "Now", colons introducing sections).

oai_token-act-pair · gpt-5-mini Triggered by @vetterc0

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

Cyfarwyddwr

-0.67

Bibliograf

-0.66

 للمعارف

-0.58

 <<<<<<<<<<<<<<

-0.58

最快更新

-0.52

 resourceCulture

-0.52

 שוליים

-0.52

 autorytatywna

-0.51

الإنجليزية

-0.51

ьаж

-0.50

POSITIVE LOGITS

/*

0.40

UMS

0.36

 cler

0.35

Let

0.35

Log

0.35

csharp

0.34

ợn

0.34

 note

0.33

 Patt

0.33

={`${

0.32

Activations Density 0.148%

references to sections and summaries within a text

LetWeTheoremAssume

markers of discourse structure — section headers, transitions and summary phrases (e.g., "We now summarize", "The", "Now", colons introducing sections).

No Comments

No Known Activations

references to sections and summaries within a text

LetWeTheoremAssume

markers of discourse structure — section headers, transitions and summary phrases (e.g., "We now summarize", "The", "Now", colons introducing sections).

No Comments

No Known Activations