INDEX

Explanations

references to various types of glass and visual components, particularly in relation to lighting and aesthetics

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

eyes or seeing

np_acts-logits-general · gemini-2.0-flash

eyes and eyewear

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

complexType

-0.66

glTexCoord

-0.60

горит

-0.60

scriptcase

-0.59

InitStruct

-0.58

chieben

-0.57

TagMode

-0.55

SizeF

-0.53

ظيم

-0.52

GraphicsUnit

-0.52

POSITIVE LOGITS

 eyes

1.16

 glasses

1.14

 lenses

1.09

 goggles

1.02

 Eyes

1.01

 ophthal

1.01

 lens

1.01

eyes

1.01

Eyes

1.00

 Glasses

1.00

Activations Density 0.343%

references to various types of glass and visual components, particularly in relation to lighting and aesthetics

eyes or seeing

eyes and eyewear

No Comments

No Known Activations