INDEX

Explanations

phrases associated with duration, particularly those emphasizing long-term concepts or commitments

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

tonode

-0.61

plaatst

-0.59

gemaakt

-0.58

 encontram

-0.57

 AssemblyTitle

-0.54

 surpresa

-0.51

PerSecond

-0.51

AddWithValue

-0.51

})));

-0.50

oredCriteria

-0.49

POSITIVE LOGITS

 term

1.06

ago

1.03

term

0.88

Term

0.87

 Term

0.85

lasting

0.83

 lasting

0.83

gggg

0.78

 TERM

0.78

 overdue

0.76

Activations Density 0.147%

phrases associated with duration, particularly those emphasizing long-term concepts or commitments

No Comments

No Known Activations