INDEX

Explanations

elements in structured data or layout specifications

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

 nakalista

-1.01

Хьажоргаш

-0.97

 typelib

-0.93

تقاوى

-0.88

 للمعارف

-0.88

+#+#

-0.86

ніципа

-0.84

Демографія

-0.83

Personensuche

-0.80

 كومونز

-0.80

POSITIVE LOGITS

SpringBootTest

0.49

MessageTagHelper

0.43

ве

0.40

čas

0.40

lė

0.38

 Wikidata

0.38

weta

0.36

livé

0.36

</h2>

0.36

Activations Density 1.196%

elements in structured data or layout specifications

No Comments

No Known Activations