INDEX

Explanations

evidence and indications of relationships or outcomes

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

Followed by "that."

np_acts-logits-general · gemini-2.0-flash

indicate or suggest something

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

每一次

-0.53

 maxHeight

-0.51

 cough

-0.51

OOTDTY

-0.50

credited

-0.50

 Volga

-0.49

 Macromolecules

-0.49

 endfor

-0.49

 deleteAll

-0.49

 MacArthur

-0.49

POSITIVE LOGITS

それだけ

0.91

 either

0.82

Either

0.80

 Either

0.78

webElementXpaths

0.76

 serious

0.74

cheinend

0.72

 demek

0.71

either

0.71

tagHelperRunner

0.70

Activations Density 0.429%

evidence and indications of relationships or outcomes

Followed by "that."

indicate or suggest something

No Comments

No Known Activations

evidence and indications of relationships or outcomes

Followed by "that."

indicate or suggest something

No Comments

No Known Activations