INDEX

Explanations

code constructs related to interface definitions and implementations

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

Tokens preceding implemented interfaces

np_acts-logits-general · gemini-2.0-flash

code interfaces and implementations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.45

-0.42

 under

-0.42

em

-0.40

vi

-0.39

dem

-0.38

-0.37

度

-0.37

POSITIVE LOGITS

IInterface

1.11

InjectAttribute

1.04

 nahilalakip

1.01

IContainer

0.99

 незавершена

0.99

IBase

0.97



0.96

interfaces

0.96

oredCriteria

0.95

0.91

Activations Density 0.192%

code constructs related to interface definitions and implementations

Tokens preceding implemented interfaces

code interfaces and implementations

No Comments

No Known Activations