INDEX

Explanations

references to individuals or groups in a narrative context

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

behaviours from other patients i knew

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

-0.60

-0.45

。

-0.40

 includes

-0.39

↵

-0.39

 therefore

-0.38

↵↵

-0.38

 also

-0.38

 with

-0.35

 through

-0.35

POSITIVE LOGITS

IUrlHelper

1.26

 виправивши

1.03

ロウィン

1.02

ValueStyle

1.02

tvguidetime

1.00

 queſta

0.98

 Waſſer

0.97

 tartalomajánló

0.95

ésultats

0.95

<unused41>

0.94

Activations Density 0.053%

references to individuals or groups in a narrative context

behaviours from other patients i knew

No Comments

No Known Activations