INDEX

Explanations

references to proximity or closeness

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

IsMutable

-0.66

sprogramm

-0.62

漿

-0.57

Abp

-0.56

yntax

-0.53

TypedDataSet

-0.51

lasm

-0.50

 مشين

-0.50

 Baillargeon

-0.50

splan

-0.50

POSITIVE LOGITS

 proximity

1.26

 Proximity

0.94

 Close

0.88

 close

0.87

 CLOSE

0.86

Close

0.84

Proximity

0.80

 approximation

0.79

 closeness

0.79

CLOSE

0.79

Activations Density 0.073%

references to proximity or closeness

No Comments

No Known Activations