INDEX

Explanations

patterns and structures in data representation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 Escor

-0.63

 gostar

-0.61

 céré

-0.60

orologio

-0.60

 kohta

-0.58

 Numa

-0.57

 adesi

-0.56

 kiin

-0.56

ägg

-0.56

 Tertiary

-0.56

POSITIVE LOGITS

lamabad

0.62

Хьажоргаш

0.62

WithIOException

0.57

imming

0.54

ne

0.54

&__

0.53

uito

0.53

 فريبيس

0.53

uxxxx

0.53

qrstuvwxyz

0.51

Activations Density 0.481%

patterns and structures in data representation

No Comments

No Known Activations