INDEX

Explanations

negations and expressions of disbelief or disagreement

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

Followed by adverbs of negation

np_acts-logits-general · gemini-2.0-flash

negation of expectations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

webElementXpaths

-0.72

WithIOException

-0.68

OGND

-0.65

 nahilalakip

-0.63

ChildScrollView

-0.61

thâu

-0.58

Aholisi

-0.54

MessageWindow

-0.53

Derbyniad

-0.53

RenderAtEndOf

-0.53

POSITIVE LOGITS

 necessarily

0.38

 ground

0.35

 déb

0.33

 golden

0.33

 dissimilar

0.31

 masakan

0.31

 rocket

0.31

+}\

0.30

źć

0.30

 earth

0.30

Activations Density 0.339%

negations and expressions of disbelief or disagreement

Followed by adverbs of negation

negation of expectations

No Comments

No Known Activations