INDEX

Explanations

specific names or identifiers related to individuals, locations, or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

قایناقلار

-0.68

 autorytatywna

-0.59

脚注の使い方

-0.58

Erreferentziak

-0.57

 viewType

-0.56

 חיצוניים

-0.54

 CanadaChoose

-0.53

 esternos

-0.52

 initComponents

-0.50

Yep

-0.50

POSITIVE LOGITS

Bises

0.60

GHIJKLM

0.55

 Carboniferous

0.55

पुर

0.54

 motivadoras

0.54

uxxxx

0.54

Nobel

0.53

Avantages

0.52

NUMX

0.51

 ακόμα

0.49

Activations Density 0.268%

specific names or identifiers related to individuals, locations, or entities

No Comments

No Known Activations