INDEX

Explanations

expressions indicating knowledge or awareness

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

 tartalomajánló

-1.25

 Theſe

-0.82

Datuak

-0.82

libft

-0.76

 Chrift

-0.75

tiérrez

-0.74

ghijkl

-0.72

 Monfieur

-0.69

GEBURTSDATUM

-0.68

 Jefus

-0.68

POSITIVE LOGITS

 many

0.53

 tudom

0.53

 sappiamo

0.52

 conozco

0.51

 sicuramente

0.50

 loved

0.50

 though

0.49

WebVitals

0.49

 wiem

0.48

rogels

0.47

Activations Density 0.086%

expressions indicating knowledge or awareness

No Comments

No Known Activations