INDEX

Explanations

tokens related to actions of throwing or related activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

endregion

-0.61

 vallée

-0.57

+#+#

-0.57

else

-0.56

 independientes

-0.54

 Venise

-0.54

IConfiguration

-0.52

 Beards

-0.51

 huellas

-0.51

 }^{*}

-0.51

POSITIVE LOGITS

 throw

1.75

 thrown

1.65

 throwing

1.61

 threw

1.59

 Throw

1.52

 throws

1.52

 toss

1.48

 Throwing

1.48

 tossing

1.43

throwing

1.43

Activations Density 0.129%

tokens related to actions of throwing or related activities

No Comments

No Known Activations