INDEX

Explanations

active verbs that indicate action or engagement

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

preceding URLs or links

np_acts-logits-general · gemini-2.0-flash

promoting successful outcomes

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 estiver

-0.47

 TestBed

-0.46

 sureties

-0.43

Morning

-0.42

 jakość

-0.41

ROIT

-0.40

dstuk

-0.40

 useEffect

-0.40

ことはない

-0.39

cha

-0.39

POSITIVE LOGITS

 link

0.77

MLLoader

0.77

 링크

0.74

 ACTION

0.73

 action

0.72

 Action

0.71

 click

0.70

 hyperlink

0.69

Action

0.69

ACTION

0.69

Activations Density 0.282%

active verbs that indicate action or engagement

preceding URLs or links

promoting successful outcomes

No Comments

No Known Activations