INDEX

Explanations

instances of the word "decide" and its variations, indicating decisions or choices being made

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

"decided" or "decides"

np_acts-logits-general · gemini-2.0-flash

making a decision or conclusion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

béco

-0.57

posedge

-0.55

altro

-0.52

DebuggerNonUser

-0.50

 bezeichneter

-0.49

 "..\..\

-0.49

 indication

-0.49

 Biôgrafia

-0.49

 Transitions

-0.48

انجليز

-0.48

POSITIVE LOGITS

 décidé

0.72

 initComponents

0.71

Against

0.70

 Decided

0.70

GenerationType

0.70

 Against

0.70

 against

0.68

 AGAINST

0.66

 decided

0.62

 continúas

0.62

Activations Density 0.104%

instances of the word "decide" and its variations, indicating decisions or choices being made

"decided" or "decides"

making a decision or conclusion

No Comments

No Known Activations