INDEX

Explanations

phrases indicating consequences or reactions related to policy decisions

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

Follows a conjunction/adverb

np_acts-logits-general · gemini-2.0-flash

skepticism and criticism

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 wonderful

-0.59

 nahilalakip

-0.55

 meravigli

-0.54

 merveille

-0.54

 skall

-0.53

wonderful

-0.52

 correcte

-0.52

 مشين

-0.50

 mentira

-0.50

 الأصل

-0.48

POSITIVE LOGITS

 critics

0.82

 مرئيه

0.79

Critics

0.76

 Critics

0.70

 lenker

0.69

 tensions

0.69

Analysts

0.69

 skepticism

0.67

 skep

0.67

 amid

0.67

Activations Density 0.287%

phrases indicating consequences or reactions related to policy decisions

Follows a conjunction/adverb

skepticism and criticism

No Comments

No Known Activations