INDEX

Explanations

technical terms and parameters related to scientific measurements or calculations

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

interopRequire

-0.53

ioutil

-0.48

териалы

-0.48

SerializeField

-0.47

WriteAttribute

-0.46

('../../../

-0.43

pahan

-0.43

putExtra

-0.43

dote

-0.42

typeparam

-0.41

POSITIVE LOGITS

 >=",

0.91

WithIOException

0.81

 propOrder

0.70

Derbyniad

0.69

LabelTagHelper

0.69

 pylint

0.67

 Shakspeare

0.67

CloseOperation

0.66

 distanciation

0.66

 LoggerFactory

0.65

Activations Density 3.843%

technical terms and parameters related to scientific measurements or calculations

No Comments

No Known Activations