INDEX

Explanations

programming structures and elements related to class and repository definitions in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 entgegen

-0.53

 Anspruch

-0.46

 дел

-0.45

 Kenntnis

-0.45

 mecanismos

-0.45

sikan

-0.44

 Jones

-0.44

 foco

-0.43

struct

-0.43

 recently

-0.43

POSITIVE LOGITS

InputBorder

0.74

OrNil

0.60

ſelves

0.60

fjspx

0.58

IUrlHelper

0.57

 Мексичка

0.57

 depositphotos

0.56

oredCriteria

0.56

ſelf

0.55

лактика

0.55

Activations Density 0.033%

programming structures and elements related to class and repository definitions in code

No Comments

No Known Activations