INDEX

Explanations

non-English words or phrases that indicate actions or states

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

Preceding a Japanese word, punctuation, or preposition

np_acts-logits-general · gemini-2.0-flash

past tense verbs

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

quelize

-0.68

 snippetHide

-0.68

 disambiguazione

-0.67

Composable

-0.64

 تكبرها

-0.64

AndEndTag

-0.64

kháu

-0.62

 فريبيس

-0.62

isable

-0.60

gotten

-0.60

POSITIVE LOGITS

did

0.83

Did

0.70

Did

0.69

did

0.66

 took

0.61

took

0.59

was

0.56

 gave

0.55

 arose

0.54

了

0.54

Activations Density 0.060%

non-English words or phrases that indicate actions or states

Preceding a Japanese word, punctuation, or preposition

past tense verbs

No Comments

No Known Activations