INDEX

Explanations

numerical values indicating measurements or quantities

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

-0.92

-0.81

-0.80

-0.79

-0.77

ly

-0.75

POSITIVE LOGITS

 feroit

1.14

^(@)

1.06

 wikipagina

1.05

 pouvoit

1.03

 auroit

1.03

 mauva

1.03

 avoient

1.01

 ainfi

0.98

 plufieurs

0.97

 dévelo

0.97

Activations Density 0.642%

numerical values indicating measurements or quantities

No Comments

No Known Activations