INDEX

Explanations

references to the word "ring" in various contexts, such as physical objects, mathematical concepts, or structural elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

addContainerGap

-1.03

PerformLayout

-1.00

存于互联网档案馆

-0.89

 Mojave

-0.87

 McCabe

-0.85

__*/

-0.84

 McDowell

-0.83

texttt

-0.82

 robots

-0.81

Filmografie

-0.81

POSITIVE LOGITS

Ing

1.31

Ing

1.27

ING

1.15

 LING

1.07

ring

1.06

ling

1.05

ng

1.05

 RING

0.99

ning

0.97

 rings

0.97

Activations Density 0.168%

references to the word "ring" in various contexts, such as physical objects, mathematical concepts, or structural elements

No Comments

No Known Activations