INDEX

Explanations

mentions of data source configurations in programming contexts

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

python aws sdk

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

 Schwartz

-0.42

romyalgia

-0.40

ldern

-0.39

 stiff

-0.38

ifying

-0.37

ismuth

-0.37

 Revolt

-0.37

clusão

-0.37

 quiet

-0.37

 silent

-0.37

POSITIVE LOGITS

['$

1.16

 AssemblyVersion

0.67

EndGlobalSection

0.66

rungsseite

0.63

InjectAttribute

0.59

IndentedString

0.57

tagPool

0.55

yntaxException

0.55

createClass

0.54

 censiti

0.53

Activations Density 0.000%

mentions of data source configurations in programming contexts

python aws sdk

No Comments

No Known Activations