INDEX

Explanations

numerical references and dates

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

 Baillargeon

-0.69

 autorytatywna

-0.67

Демографія

-0.65

 AssemblyCulture

-0.63

serviceWorker

-0.63

 Plut

-0.61

 Venn

-0.61

KommentareTeilen

-0.60

 Carmel

-0.60

الدراسه

-0.59

POSITIVE LOGITS

enumi

0.90

édrale

0.55

 发表于

0.55

dymyr

0.54

HasOne

0.52

enumii

0.50

 Dernière

0.49

 Last

0.49

 last

0.48

RUnlock

0.48

Activations Density 0.136%

numerical references and dates

No Comments

No Known Activations