INDEX

Explanations

phrases related to lists and organization

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

 déchir

-0.63

 điệu

-0.58

렇

-0.55

ഠ

-0.52

 Clever

-0.51

assioned

-0.51

твор

-0.50

fél

-0.50

 крайней

-0.50

kových

-0.50

POSITIVE LOGITS

kuuta

0.85

 ModelExpression

0.82

 AspNetCore

0.80

ⓧ

0.78

BufferException

0.76

 yılında

0.75

Rüyada

0.74

 UIFont

0.72

 насељу

0.72

UDC

0.71

Activations Density 0.089%

phrases related to lists and organization

No Comments

No Known Activations

phrases related to lists and organization

No Comments

No Known Activations