INDEX

Explanations

complexity-related terminology in computational theory

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

BeginInit

-0.52

copyWith

-0.48

IActionResult

-0.47

 BorderSide

-0.46

حياته

-0.45

δη

-0.45

enderror

-0.45

Erstellt

-0.44

stag

-0.44

gung

-0.44

POSITIVE LOGITS

icali

0.67

anguages

0.67

SourceChecksum

0.64

Gare

0.64

oluble

0.58

antuan

0.57

RenderAtEndOf

0.55

 décid

0.55

createCanvas

0.54

 Wreath

0.54

Activations Density 2.077%

complexity-related terminology in computational theory

No Comments

No Known Activations