INDEX

Explanations

references to the term "spark" in various contexts

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

spark, sparked, SparkFun

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

Hochspringen

-0.48



-0.47

 overridden

-0.46

 Meto

-0.44

Nei

-0.44

 تعدى

-0.44

wain

-0.42

->

-0.41

Hun

-0.41

 ControllerBase

-0.40

POSITIVE LOGITS

 Spark

1.03

Spark

1.02

 SPARK

0.98

Sparks

0.94

 Sparks

0.93

 spark

0.93

spark

0.90

 sparks

0.84

 sparkle

0.75

 pleaſure

0.75

Activations Density 0.004%

references to the term "spark" in various contexts

spark, sparked, SparkFun

No Comments

No Known Activations