INDEX

Explanations

terms related to user creation and database interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/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.9.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

ablon

-0.61

 pinulongan

-0.59

 kaarangay

-0.59

 newName

-0.57

 groupName

-0.56

็ต

-0.55

 CURIAM

-0.55

 colle

-0.54

rativa

-0.53

 चीज़ों

-0.53

POSITIVE LOGITS

mybatisplus

0.67

 sumpay

0.61

findOne

0.58

 blessés

0.57

JpaRepository

0.57

 فريبيس

0.57

setopt

0.56

quelize

0.53

findById

0.52

 épaules

0.52

Activations Density 0.032%

terms related to user creation and database interactions

No Comments

No Known Activations