INDEX

Explanations

scientific terms and statistical language related to research findings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

Efq

-0.68

Sucesor

-0.67

 Theſe

-0.65

 Diſ

-0.64

 RIPRODUZIONE

-0.63

 dreamstime

-0.61

 vectoriales

-0.60

 turísticos

-0.60

Šaltiniai

-0.60

 nôtre

-0.60

POSITIVE LOGITS

ChildScrollView

0.78

 numerus

0.76

 well

0.62

 most

0.60

%")

0.58

KURZBESCHREIBUNG

0.57

but

0.57

]));

0.57

gridy

0.55

})`

0.54

Activations Density 3.885%

scientific terms and statistical language related to research findings

No Comments

No Known Activations