INDEX

Explanations

variables, parameters, and function expressions related to statistical and mathematical modeling

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

Tokens that end in "p"

np_acts-logits-general · gemini-2.0-flash

words ending in 'ip' or 'ep'

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

\"");

-0.49

er

-0.49

javax

-0.47

/**

-0.45

 "'");

-0.43

/>";

-0.43

.”.

-0.42

/*!

-0.40

"";

-0.40

 "");

-0.40

POSITIVE LOGITS

Jep

0.81

lp

0.79

Lep

0.77

Kip

0.77

pyp

0.76

nep

0.76

Lep

0.75

yp

0.75

rep

0.73

ep

0.72

Activations Density 2.451%

variables, parameters, and function expressions related to statistical and mathematical modeling

Tokens that end in "p"

words ending in 'ip' or 'ep'

No Comments

No Known Activations