INDEX

Explanations

class or interface definitions in code, particularly those that extend or implement other classes or interfaces

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 SQLException

-0.48

 Akhtar

-0.45

ButtonModule

-0.44

的食物

-0.44

logen

-0.44

 OMIT

-0.44

ielli

-0.43

 would

-0.43

cul

-0.43

 string

-0.42

POSITIVE LOGITS

Base

1.05

Abstract

1.00

 MonoBehaviour

0.98

 Base

0.95

base

0.95

BaseActivity

0.93

 Abstract

0.93

 base

0.89

 getBase

0.85

abstract

0.84

Activations Density 0.078%

class or interface definitions in code, particularly those that extend or implement other classes or interfaces

No Comments

No Known Activations