INDEX

Explanations

references to grains and their properties in a material context

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

grain properties and types

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

 betweenstory

-0.75

Ome

-0.59

ſelf

-0.57

 Lipa

-0.56

fjspx

-0.54

 surla

-0.53

Alp

-0.51

lun

-0.51

 Wonderland

-0.49

 Opti

-0.49

POSITIVE LOGITS

 grain

1.19

Grain

1.16

 Grain

1.13

grain

1.10

grained

0.90

 granos

0.87

 grano

0.82

 grains

0.81

grains

0.79

 grained

0.77

Activations Density 0.013%

references to grains and their properties in a material context

grain properties and types

No Comments

No Known Activations