INDEX

Explanations

coding and programming-related terms, especially those associated with hardware architecture and structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

RegressionTest

-0.57

TagMode

-0.55

Jereo

-0.53

@"/

-0.53

WriteAttribute

-0.52

 façons

-0.51

:].

-0.51

 diantaranya

-0.50

 Partagez

-0.49

 decoracion

-0.48

POSITIVE LOGITS

 للمعارف

0.83

sidemargin

0.69

 invokingState

0.69

mybatisplus

0.67

PyExc

0.66

 linkovi

0.60

 المعيارى

0.58

expandindo

0.56

nonatomic

0.56

 MonoBehaviour

0.56

Activations Density 0.405%

coding and programming-related terms, especially those associated with hardware architecture and structures

No Comments

No Known Activations