INDEX

Explanations

mathematical expressions and notations

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

-0.60

-0.52

[]

-0.52

Bar

-0.51

 void

-0.50

bar

-0.50

thâu

-0.48

fan

-0.47

POSITIVE LOGITS

 avoient

0.97

 feroit

0.96

 étoit

0.93

 auroit

0.90

 étoient

0.88

}}}}

0.88

 pouvoit

0.85

 ainfi

0.81

}}}

0.81

)))))

0.81

Activations Density 1.056%

mathematical expressions and notations

No Comments

No Known Activations