INDEX

Explanations

technical terms and components related to programming and software development

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

Tokens surrounded by underscores

np_acts-logits-general · gemini-2.0-flash

figures and code snippets

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

migrationBuilder

-0.65

addContainerGap

-0.60

 unknownFields

-0.59

$_['

-0.57

stateMutability

-0.55

日閲覧

-0.55

-0.51

resultCode

-0.50

Traceback

-0.49

cemment

-0.49

POSITIVE LOGITS

$_

0.66

0.60

}}_

0.57

 Loyal

0.55

__

0.54

 consultato

0.54

دانشنامهٔ

0.53

 unbound

0.52

 Burnley

0.51

]_

0.51

Activations Density 1.362%

technical terms and components related to programming and software development

Tokens surrounded by underscores

figures and code snippets

No Comments

No Known Activations