INDEX

Explanations

instances of the word 'posted' and variations of it

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

getColumnIndex

-0.94

ArgsConstructor

-0.86

sizeCache

-0.75

-0.74

 CoreData

-0.68

 MonoBehaviour

-0.66

JoinColumn

-0.64

endregion

-0.63

Ken

-0.62

ற்று

-0.62

POSITIVE LOGITS

 themſelves

1.27

 myſelf

1.27

 posted

1.21

 itſelf

1.18

 whoſe

1.11

 Theſe

1.08

 posting

1.06

Efq

1.06

 Posting

1.05

 Shakspeare

1.05

Activations Density 0.178%

instances of the word 'posted' and variations of it

No Comments

No Known Activations