INDEX

Explanations

references to people and locations, especially in a research or conservation context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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



-0.79

 lenker

-0.78

 Theſe

-0.74

 myſelf

-0.74

 Monfieur

-0.73

PerformLayout

-0.71

 Anſ

-0.70

 мәкал

-0.70

دانشنامهٔ

-0.69

 Jefus

-0.69

POSITIVE LOGITS

à

0.56

0.54

 Barcelona

0.53

ò

0.53

Barcelona

0.52

 Antoni

0.50

 Josep

0.50

àng

0.48

 Nadal

0.48

 braços

0.47

Activations Density 0.047%

references to people and locations, especially in a research or conservation context

No Comments

No Known Activations