INDEX

Explanations

expressions that relate to computational complexity and algorithm analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

Rohy

-0.50

GeneratedValue

-0.49

actéristique

-0.48

Skocz

-0.46

kuuta

-0.45

Personensuche

-0.45

Hochspringen

-0.45

Nonnull

-0.45

 esternos

-0.45

endpush

-0.45

POSITIVE LOGITS

1.00

 complexity

0.97

0.89

 logarithmic

0.78

 complexities

0.77

 linear

0.77

complexity

0.76

Complexity

0.76

 Complexity

0.72

 complejidad

0.69

Activations Density 0.918%

expressions that relate to computational complexity and algorithm analysis

No Comments

No Known Activations