INDEX

Explanations

programming-related keywords associated with functions and method declarations

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

Code and special characters

np_acts-logits-general · gemini-2.0-flash

initialization, assignment, or follow-up context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

ptons

-0.57

üğ

-0.56

 tolua

-0.54

]<<"

-0.54

 Numerade

-0.52

最快更新

-0.50

ệu

-0.49

meaning

-0.47

riwal

-0.47

 meaning

-0.46

POSITIVE LOGITS

IndentedString

0.59

isContained

0.59

principalTable

0.58

drawSprites

0.57

 piele

0.57

ItemBackground

0.53

 BoxDecoration

0.52

 rather

0.51

 LoggerFactory

0.50

 snippetHide

0.50

Activations Density 0.098%

programming-related keywords associated with functions and method declarations

Code and special characters

initialization, assignment, or follow-up context

No Known Activations