INDEX

Explanations

numerical values and their associations

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

Numbers followed by parenthesis

np_acts-logits-general · gemini-2.0-flash

numbers in parentheses

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

 must

-0.66

must

-0.62

下载附件

-0.61

brainly

-0.60

orsese

-0.58

gige

-0.57

 Must

-0.54

 måste

-0.53

kuuta

-0.52

 Paglinawan

-0.52

POSITIVE LOGITS

AnchorStyles

0.71

0.69

 ModelExpression

0.66

0.64

0.61

0.60

TestingModule

0.59

0.57

日閲覧

0.55

Activations Density 0.988%

numerical values and their associations

Numbers followed by parenthesis

numbers in parentheses

No Comments

No Known Activations