INDEX

Explanations

phrases related to computer architecture and definitions

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

Code, macros, and definitions

np_acts-logits-general · gemini-2.0-flash

code definitions and documentation

np_acts-logits-general · gemini-2.5-flash-lite

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

GHIJKLM

-0.49

Explicación

-0.47

kkit

-0.47

SRM

-0.47

qld

-0.47

wende

-0.46

Spoljašnje

-0.46

ntgen

-0.46

 المض

-0.45

udge

-0.45

POSITIVE LOGITS

 CreateTagHelper

1.00

NameInMap

0.93

findpost

0.92

AccessorTable

0.84

 ProtoMessage

0.80

出版年

0.69

SharedCtor

0.68

 raiſ

0.67

parsedMessage

0.66

 propOrder

0.64

Activations Density 0.426%

phrases related to computer architecture and definitions

Code, macros, and definitions

code definitions and documentation

No Comments

No Known Activations