INDEX

Explanations

references to aspects or features of concepts, objects, or ideas

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

aspect ratio

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

Lau

-0.46

 Wilkes

-0.46

laundry

-0.46

 Prepar

-0.43

nls

-0.43

 ceremon

-0.43

oretical

-0.42

knitted

-0.41

embroidered

-0.41

laund

-0.41

POSITIVE LOGITS

 aspect

1.86

aspect

1.65

 Aspect

1.45

Aspect

1.41

 aspecto

1.06

 facet

1.04

 aspetto

0.94

aspetto

0.94

 aspek

0.80

 component

0.75

Activations Density 0.007%

references to aspects or features of concepts, objects, or ideas

aspect ratio

No Comments

No Known Activations