INDEX

Explanations

instances of the word "strike" or its variations in different contexts

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

"strike" and "striking"

np_acts-logits-general · gemini-2.0-flash

strike and variants

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

escens

-0.59

Entities

-0.55

 Sagan

-0.55

gouv

-0.55

luri

-0.55

nextPage

-0.54

orElse

-0.53

cemment

-0.53

 Hügel

-0.52

McN

-0.52

POSITIVE LOGITS

 Strikes

1.61

 strikes

1.56

 strike

1.51

 Strike

1.50

Strike

1.46

 striking

1.38

strike

1.37

 struck

1.26

 Striking

1.26

Stri

1.11

Activations Density 0.114%

instances of the word "strike" or its variations in different contexts

"strike" and "striking"

strike and variants

No Comments

No Known Activations