INDEX

Explanations

references to specific belief systems or ideologies

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

Word preceding a verb

np_acts-logits-general · gemini-2.0-flash

things that produce

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 Parcelable

-0.51

WithIdentifier

-0.48

Javadoc

-0.48

เอง

-0.48

Hearing

-0.46

ayant

-0.46

 réguli

-0.46

+:+

-0.45

 CascadeType

-0.45

 Baumann

-0.44

POSITIVE LOGITS

awtextra

0.67

 entails

0.67

pexpr

0.67

ThroughAttribute

0.63

dagogik

0.58

IVEREF

0.58

 would

0.57

 might

0.56

évaluateur

0.56

Autoritní

0.56

Activations Density 0.263%

references to specific belief systems or ideologies

Word preceding a verb

things that produce

No Comments

No Known Activations