INDEX

Explanations

references to specific studies and authors in scientific literature

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

^(@)

-0.67

endwhile

-0.63

Voltaje

-0.63

cemment

-0.60

walde

-0.60

gero

-0.59

kuuta

-0.58

yarnpkg

-0.58

Cordialement

-0.57

devant

-0.57

POSITIVE LOGITS

 "..\..\

0.61

Personensuche

0.60

StoryboardSegue

0.59

et

0.57

 Signalez

0.57

tagext

0.56

ATRE

0.56

BSc

0.55

 Lordships

0.55

 Roskov

0.54

Activations Density 0.495%

references to specific studies and authors in scientific literature

No Comments

No Known Activations