INDEX

Explanations

phrases indicating conditions or states of being

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

many or few

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

routeProvider

-0.55

zepam

-0.48

CGRectMake

-0.44

withIdentifier

-0.44

 SEPAR

-0.44

=$((

-0.43

Referències

-0.43

Ӕ

-0.43

 الاطلاع

-0.42

GetAxis

-0.42

POSITIVE LOGITS

多い

1.33

が多い

1.13

ことが多い

1.03

も多い

1.01

やすい

0.80

が多

0.76

が多く

0.74

多かった

0.74

しやすい

0.71

많

0.70

Activations Density 0.005%

phrases indicating conditions or states of being

many or few

No Comments

No Known Activations