INDEX

Explanations

mathematical notation and symbols

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

simplify matters

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

 conmigo

-0.63

ByVersion

-0.62

 <>",

-0.62

</tfoot>

-0.61

 nakalista

-0.61

 typelib

-0.59

 estekak

-0.59

fromnode

-0.58

قایناق‌لار

-0.57

RegressionTest

-0.56

POSITIVE LOGITS

0.65

0.45

gray

0.45

sch

0.44

0.41

firm

0.40

tw

0.40

 Future

0.39

Gön

0.39

 ValueError

0.39

Activations Density 0.000%

mathematical notation and symbols

simplify matters

No Comments

No Known Activations