INDEX

Explanations

the word "ron" and its variations in different cases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 Wikimedijinoj

-0.75

ElementException

-0.72

Tikang

-0.70

vábbi

-0.67

 autorytatywna

-0.67

 дописавши

-0.67

 AssemblyTitle

-0.66

 Италијани

-0.65

thâu

-0.64

TableField

-0.64

POSITIVE LOGITS

Tazama

0.63

yes

0.60

eta

0.56

 Leaks

0.55

nps

0.54

Sustain

0.54

 elegans

0.54

かね

0.53

nha

0.51

 Вікі

0.51

Activations Density 0.238%

the word "ron" and its variations in different cases

No Comments

No Known Activations