INDEX

Explanations

phrases related to actions directed at individuals and their consequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

спе

-0.45

basicConfig

-0.40

-0.39

we

-0.38

↵↵

-0.38

freep

-0.38

We

-0.37

تر

-0.37

Ver

-0.36

Sucesor

-0.36

POSITIVE LOGITS

GEBURTSDATUM

0.91

 universe

0.91

 heaven

0.90

 تضيفلها

0.89

 Universe

0.84

 earth

0.80

 EconPapers

0.80

 heavens

0.79

universe

0.79

 moon

0.78

Activations Density 0.273%

phrases related to actions directed at individuals and their consequences

No Comments

No Known Activations