INDEX

Explanations

references to categorization or organization by specific criteria

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

parsedMessage

-0.67

AccessorTable

-0.66

VersionUID

-0.63

WithIOException

-0.49

 kysy

-0.47

 klä

-0.45

StoreMessageInfo

-0.45

()?;

-0.45

 QtGui

-0.45

 Humanos

-0.44

POSITIVE LOGITS

 gender

0.79

mybatisplus

0.77

fastjson

0.67

gender

0.60

 Gender

0.57

 geographic

0.55

 cụ

0.53

schild

0.52

Gender

0.52

 geographical

0.51

Activations Density 0.391%

references to categorization or organization by specific criteria

No Comments

No Known Activations