INDEX

Explanations

statistical references and data analysis terminology

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

citations and references

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

featureID

-0.54

########.

-0.47

 FetchType

-0.47

 Schluß

-0.47

providedIn

-0.46

ConstraintMaker

-0.46

 ConstraintSet

-0.46

 doccia

-0.45

interopRequire

-0.45

ragalactic

-0.44

POSITIVE LOGITS

enterOuterAlt

0.40

autorest

0.40

UserScript

0.40

tagHelperRunner

0.38

Välislingid

0.36

 communiquez

0.35

 bénéficiaire

0.34

 CYTHON

0.33

ResponseWriter

0.32

 Infórmanos

0.32

Activations Density 0.011%

statistical references and data analysis terminology

citations and references

No Comments

No Known Activations