INDEX

Explanations

phrases that denote affiliation or possession

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

set of

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

Referències

-0.50

 EconPapers

-0.47

 penyebab

-0.44

the

-0.44

OGND

-0.43

 onAnimation

-0.41

 صوتيه

-0.41

 wireType

-0.41

AutoScaleMode

-0.41

">//

-0.40

POSITIVE LOGITS

ɕ

0.50

csolódó

0.50

期刊论文

0.48

ilai

0.47

NOPQRST

0.45

estris

0.44

ocular

0.43

ayana

0.43

olyn

0.43

otides

0.42

Activations Density 0.058%

phrases that denote affiliation or possession

set of

No Comments

No Known Activations