INDEX

Explanations

comparison operators in code or technical language

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

greater than or equal to

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

Negative Logits

ArgumentParser

-0.42

 Sucher

-0.40

học

-0.38

๋

-0.37

 songs

-0.37

 muchacha

-0.36

pyplot

-0.35

 passagers

-0.35

*}$

-0.35

POSITIVE LOGITS

>=

2.02

>=

1.74

)>=

1.63

]>=

1.60

'>=

1.17

">=

1.16

geq

1.13

≥

1.08

≥

1.05

geqslant

0.81

Activations Density 0.033%

comparison operators in code or technical language

greater than or equal to

No Known Activations