INDEX

Explanations

names and categories related to media and entertainment

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

存于互联网档案馆

-0.95

)");

-0.95

Enllaces

-0.94

 kasarigan

-0.94

########.

-0.93

 Roskov

-0.93

GEBURTSDATUM

-0.91

abestanden

-0.89

abstractmethod

-0.86

 Administrativna

-0.86

POSITIVE LOGITS

0.49

0.47

0.45

 Luar

0.45

ear

0.44

('

0.44

th

0.43

『

0.42

Activations Density 0.177%

names and categories related to media and entertainment

No Comments

No Known Activations