INDEX

Explanations

negative qualifiers indicating absence or exclusion

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

 ſeveral

-0.70

 feveral

-0.58

PickerController

-0.56

melidir

-0.56

 ſay

-0.54

èn

-0.54

tts

-0.54

 fometimes

-0.53

 inoxydable

-0.53

 Lég

-0.53

POSITIVE LOGITS

 تضيفلها

0.94

AndEndTag

0.82

(!__

0.78

 Италијани

0.76

 ohne

0.67

ⓧ

0.65

 without

0.64

protoimpl

0.64

ArrowToggle

0.63

IntoConstraints

0.61

Activations Density 0.688%

negative qualifiers indicating absence or exclusion

No Comments

No Known Activations