INDEX

Explanations

names and titles of people, places, or proper nouns in various contexts

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

Tokens before names or titles

np_acts-logits-general · gemini-2.0-flash

names and place names

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

 étoient

-0.54

 coper

-0.52

ContentAsync

-0.50

nachron

-0.50

 avoient

-0.48

 rois

-0.47

 participan

-0.47

)++;

-0.47

ZZA

-0.46

rativo

-0.46

POSITIVE LOGITS

kháu

0.83

новниш

0.69

 AssemblyVersion

0.67

Ngb

0.62

@"/

0.61

 NSCoder

0.60

signature

0.59

 StringTokenizer

0.58

 persönlich

0.56

 signature

0.56

Activations Density 0.396%

names and titles of people, places, or proper nouns in various contexts

Tokens before names or titles

names and place names

No Comments

No Known Activations