INDEX

Explanations

terms related to mathematical definitions and constructions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

期刊论文

-0.67

 prochaines

-0.65

 resourceCulture

-0.63

?;

-0.62

posedge

-0.60

RegressionTest

-0.58

enumi

-0.58

 ffilmiau

-0.57

FontOfSize

-0.57

])/

-0.56

POSITIVE LOGITS

 also

1.27

 additionally

1.04

 moreover

1.02

 again

0.99

 therefore

0.96

 furthermore

0.95

 además

0.95

also

0.94

 firstly

0.93

 besides

0.92

Activations Density 1.019%

terms related to mathematical definitions and constructions

No Comments

No Known Activations