INDEX

Explanations

technical terms and programming syntax, particularly related to URLs and code structures

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

legal, medical, and technical terms

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

bootstrapcdn

-0.58

 getattr

-0.47

centralwidget

-0.40

ogast

-0.38

glTex

-0.37

 klaar

-0.37

 Spotlight

-0.36

 tabindex

-0.36

 LUMP

-0.35

RenderAtEndOf

-0.35

POSITIVE LOGITS

yntaxException

0.43

:✨

0.43

styleType

0.42

felves

0.42

leſs

0.40

thető

0.39

Rüyada

0.37

comuna

0.37

ſelves

0.36

arities

0.36

Activations Density 0.190%

technical terms and programming syntax, particularly related to URLs and code structures

legal, medical, and technical terms

No Comments

No Known Activations