INDEX

Explanations

references to coding constructs and frameworks in software development

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 @ 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

CodeDom

-0.40

SqlClient

-0.39

 offers

-0.39

 lima

-0.36

 Schlag

-0.35

CreatedDate

-0.35

 proposals

-0.34

 contributions

-0.34

fea

-0.33

itinéraire

-0.33

POSITIVE LOGITS

########.

0.63



0.57

-------

0.56

tonode

0.54

 مرئيه

0.52

SourceChecksum

0.50

XmlAccessorType

0.49

 dAtA

0.47

 Roskov

0.47

MessageState

0.46

Activations Density 0.016%

references to coding constructs and frameworks in software development

<start_of_turn> user

No Comments

No Known Activations