INDEX

Explanations

occurrences of the word "in"

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

"In" appearing at the beginning of a sentence

np_acts-logits-general · gemini-2.0-flash

in the

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

SourceChecksum

-0.60

 Vikipedi

-0.59

 côtés

-0.58

)++;

-0.57

RenderAtEndOf

-0.56

Gön

-0.53

XmlAccessType

-0.52

UpInside

-0.51

 незавершена

-0.51

 transfieras

-0.49

POSITIVE LOGITS

 developed

0.72

 cities

0.70

 recent

0.65

 densely

0.65

 poorer

0.63

 wealthy

0.62

 industrialized

0.62

 major

0.62

developed

0.60

 całym

0.60

Activations Density 0.347%

occurrences of the word "in"

"In" appearing at the beginning of a sentence

in the

No Comments

No Known Activations