INDEX

Explanations

references to shared knowledge or common understanding

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

Follows "you know" in conversation

np_acts-logits-general · gemini-2.0-flash

you know

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

saraba

-0.87

 EconPapers

-0.87

 صوتيه

-0.81

 externi

-0.79

 EClass

-0.76

RenderAtEndOf

-0.76

bootstrapcdn

-0.76

UnsafeEnabled

-0.75

 mapStateToProps

-0.75

Chham

-0.74

POSITIVE LOGITS

 what

0.65

0.64

 those

0.64

how

0.56

cils

0.54

 like

0.54

the

0.51

pri

0.47

getApp

0.47

Activations Density 0.034%

references to shared knowledge or common understanding

Follows "you know" in conversation

you know

No Comments

No Known Activations