INDEX

Explanations

code elements and structures related to class and method definitions

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

-0.80

),

-0.66

-0.54

↵↵

-0.51

-0.49

-0.48

↵

-0.48

</strong>

-0.47

,”

-0.47

();

-0.44

POSITIVE LOGITS

Efq

1.13

StoryboardSegue

1.10

 Normdatei

1.08

 >=",

1.08

*/

1.05

 ModelExpression

1.03

Autoritní

1.03

principalColumn

1.03

*/

1.02

 autorytatywna

1.00

Activations Density 0.360%

code elements and structures related to class and method definitions

No Comments

No Known Activations