INDEX

Explanations

questions and inquiries about choices or options

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

들이

-0.54

'";

-0.51

들을

-0.51

?";

-0.51

efel

-0.49

τσι

-0.48

こんな感じで

-0.48

داية

-0.47

Przypisy

-0.47

'>";

-0.47

POSITIVE LOGITS

 Autre

0.76

 altro

0.75

msgSender

0.74

 qualunque

0.74

autre

0.73

 eenig

0.72

nother

0.71

 quelcon

0.70

 annan

0.69

 disambiguazione

0.68

Activations Density 0.552%

questions and inquiries about choices or options

No Comments

No Known Activations