INDEX

Explanations

elements and terms related to formal documentation and mathematical expressions

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

сылкі

-0.48

expandindo

-0.45

 betweenstory

-0.44

NewUrlParser

-0.44

 autorytatywna

-0.43

UrlResolution

-0.42

Alike

-0.41

 NSCoder

-0.41

 Spock

-0.40

 Lolita

-0.40

POSITIVE LOGITS

1.05

1.02

0.94

GR

0.92

 grams

0.89

GB

0.88

GP

0.88

GP

0.87

GR

0.86

Activations Density 1.693%

elements and terms related to formal documentation and mathematical expressions

No Comments

No Known Activations