INDEX

Explanations

references to programming concepts and elements related to user accounts and data models

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

ratulations

-0.67

ieteur

-0.66

MenuInflater

-0.62

--){

-0.62

$}}

-0.61

hirts

-0.60

BackPressed

-0.58

ficulty

-0.58

<",

-0.57

reportWebVitals

-0.57

POSITIVE LOGITS

:✨

0.79

mybatisplus

0.75

antd

0.70

MigrationBuilder

0.64

NameInMap

0.64

QMetaType

0.63

Besides

0.61

【

0.61

 MyBatis

0.61

 AspNetCore

0.60

Activations Density 0.194%

references to programming concepts and elements related to user accounts and data models

No Comments

No Known Activations