INDEX

Explanations

negations in various forms

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

Contractions ending with "n't"

np_acts-logits-general · gemini-2.0-flash

negative contractions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 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

 pinulongan

-0.85

 snippetHide

-0.81

GOTREF

-0.75

 Signalez

-0.75

ftagPool

-0.74

RenderAtEndOf

-0.74

GEBURTSDATUM

-0.74

 disambiguazione

-0.73

AndroidJUnit

-0.73

 GeoNames

-0.72

POSITIVE LOGITS

’

0.84

ít

0.64

ot

0.56

’”

0.53

tead

0.51

'[

0.49

”

0.49

‘

0.48

Activations Density 0.110%

negations in various forms

Contractions ending with "n't"

negative contractions

No Comments

No Known Activations