INDEX

Explanations

technical terms and references related to programming and software libraries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

RenderAtEndOf

-0.57

NameInMap

-0.56

+#+#

-0.56

 Normdatei

-0.54

 AssemblyCulture

-0.53

GenerationType

-0.50

labus

-0.50

 <<<<<<<<<<<<<<

-0.50

scryfall

-0.49

 SCHEDULE

-0.49

POSITIVE LOGITS

 Roskov

0.68

 TextStyle

0.54

ResumeLayout

0.54

andExpect

0.54

addGap

0.53

 pygame

0.53

aine

0.52

 onAnimation

0.52

 extrinsic

0.50

TypedDataSet

0.47

Activations Density 1.847%

technical terms and references related to programming and software libraries

No Comments

No Known Activations