INDEX

Explanations

names of people and geographical locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/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.10.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

paravant

-0.82

 تانيه

-0.74

المناصب

-0.73

Хьажоргаш

-0.72

appé

-0.71

ragamo

-0.70

paksa

-0.68

homonymie

-0.68

揄

-0.68

✨:

-0.67

POSITIVE LOGITS

Mad

0.66

 تضيفلها

0.64

Jo

0.61

Mad

0.57

Jo

0.55

Je

0.52

Ke

0.51

Se

0.51

AccessLevel

0.51

Mik

0.49

Activations Density 0.277%

names of people and geographical locations

No Comments

No Known Activations