INDEX

Explanations

names of specific historical or cultural terms

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

 nakalista

-0.97

GEBURTSDATUM

-0.97

WithIOException

-0.95

 وتسجيلات

-0.92

 المعيارى

-0.89

DeleteBehavior

-0.84

 كومونز

-0.83

AsUp

-0.83

UnusedPrivate

-0.79

 estekak

-0.77

POSITIVE LOGITS

lső

0.41

 villaggio

0.39

 ApiClient

0.38

ab

0.38

uestamente

0.37

 soutě

0.37

内外

0.36

 míst

0.36

 enää

0.36

 büy

0.35

Activations Density 0.299%

names of specific historical or cultural terms

No Comments

No Known Activations