INDEX

Explanations

references to content types and import statements in a programming context

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

<start_of_turn> user

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

SequentialGroup

-0.52

-0.49

?"

-0.48

 ویکی‌پدی

-0.48

-0.47

 initComponents

-0.44

-0.43

?”

-0.42

?</

-0.42

.</

-0.41

POSITIVE LOGITS

WebMethod

0.57

 myſelf

0.56

 Monfieur

0.55

 както

0.54

 Anſ

0.50

 Houſe

0.49

€,

0.49

as

0.48

&,

0.48

 plufieurs

0.47

Activations Density 0.014%

references to content types and import statements in a programming context

<start_of_turn> user

No Comments

No Known Activations