INDEX

Explanations

references to categories involving websites, films, and academic disciplines

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

"Category" labels or "ref" labels

np_acts-logits-general · gemini-2.0-flash

Category followed by colonists

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

Personendaten

-0.63

Manbalar

-0.48

UnknownFieldSet

-0.44

ніципа

-0.43

 Савезне

-0.42

Chham

-0.42

 propOrder

-0.41

UnusedPrivate

-0.40

glTexCoord

-0.40

 snippetHide

-0.40

POSITIVE LOGITS

RPG

0.47

籠

0.47

ogene

0.46

 Traps

0.45

brium

0.45

nth

0.45

 personages

0.45

 cages

0.44

 Shots

0.44

 Cage

0.44

Activations Density 2.264%

references to categories involving websites, films, and academic disciplines

"Category" labels or "ref" labels

Category followed by colonists

No Comments

No Known Activations