INDEX

Explanations

code constructs and elements related to function definitions and testing frameworks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/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.14.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

 "..\..\

-0.64

 "..\..\..\

-0.56

idey

-0.52

 Wiktionnaire

-0.52

XmlEnum

-0.52

[*

-0.52

addGap

-0.51

=’

-0.48

Skocz

-0.48

 heisst

-0.46

POSITIVE LOGITS

phazard

0.64

 Normdatei

0.60

errHandler

0.58

 kasarigan

0.58

 palsu

0.55

sizeCache

0.52

ArgsConstructor

0.49

Kanpo

0.49

enterOuterAlt

0.49

 Bioaccumulative

0.48

Activations Density 0.109%

code constructs and elements related to function definitions and testing frameworks

No Comments

No Known Activations