INDEX

Explanations

phrases indicating proximity and closeness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

yntaxException

-0.76

featureID

-0.76

IsMutable

-0.70

 ISNI

-0.64

 utafitiHapana

-0.62

OrWhiteSpace

-0.60

PerformLayout

-0.60

 Normdatei

-0.57

 OFDb

-0.57

 initComponents

-0.56

POSITIVE LOGITS

 close

3.25

close

2.71

 Close

2.61

Close

2.52

 closer

2.50

 CLOSE

2.50

 closest

2.40

 near

2.36

 closeness

2.22

CLOSE

2.13

Activations Density 0.786%

phrases indicating proximity and closeness

No Comments

No Known Activations