INDEX

Explanations

technical terms and jargon related to scientific and programming concepts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

<bos>

-0.78

TagMode

-0.76

 climático

-0.70

 avoient

-0.68

 abstrait

-0.67

transQ

-0.67

 pulmonar

-0.67

 propOrder

-0.66

ItemBackground

-0.66

 fotográfica

-0.66

POSITIVE LOGITS

enumi

0.81

protoimpl

0.71

MemoryWarning

0.69

multirow

0.60

AutoField

0.57

setcounter

0.56

 nahilalakip

0.55

Jeografia

0.54

interopRequire

0.54

Activations Density 6.288%

technical terms and jargon related to scientific and programming concepts

No Comments

No Known Activations