INDEX

Explanations

references to properties and methods of objects in programming contexts

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

underscore prefixed identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

Not in Any Lists

No Comments

Negative Logits

 autorytatywna

-0.95

RenderAtEndOf

-0.92

AndEndTag

-0.88

AddTagHelper

-0.84

Hentet

-0.80

 الحره

-0.76

تقاوى

-0.75

 feroit

-0.75

TagMode

-0.74

 Taktlose

-0.74

POSITIVE LOGITS

._

0.57

->_

0.46

private

0.42

 private

0.42

↵

0.39

own

0.38

ers

0.37

 myself

0.36

Activations Density 0.009%

references to properties and methods of objects in programming contexts

underscore prefixed identifiers

No Comments

No Known Activations