INDEX

Explanations

references to external sources and cited materials

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

Text before section numbers

np_acts-logits-general · gemini-2.0-flash

section identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

stdc

-0.54

twimg

-0.49

GEBURTSDATUM

-0.47

IntoConstraints

-0.44

libft

-0.40

 stället

-0.40

ckså

-0.39

bibfield

-0.38

 bēr

-0.37

RegressionTest

-0.37

POSITIVE LOGITS

 heading

0.55

](#

0.53

 subsections

0.52

 subsection

0.52

 Section

0.52

principalColumn

0.51

 wireType

0.50

 Heading

0.50

kloped

0.50

 section

0.49

Activations Density 1.450%

references to external sources and cited materials

Text before section numbers

section identifiers

No Comments

No Known Activations