INDEX

Explanations

phrases and terms related to performance and efficiency in technical contexts

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

Preceding adverbs of degree

np_acts-logits-general · gemini-2.0-flash

state described with intensifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.28.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

 raso

-0.37

Lep

-0.34

 EXISTING

-0.32

 buttons

-0.31

 NORMAL

-0.30

重要

-0.30

 cookies

-0.30

 genes

-0.29

 importante

-0.29

final

-0.29

POSITIVE LOGITS

 highly

0.75

 exceedingly

0.73

 extremely

0.69

 faſt

0.68

 considerably

0.66

 very

0.66

 kasarigan

0.65

 exceptionally

0.63

 oldukça

0.63

 quite

0.63

Activations Density 0.952%

phrases and terms related to performance and efficiency in technical contexts

Preceding adverbs of degree

state described with intensifiers

No Comments

No Known Activations