INDEX

Explanations

descriptive terms related to hair characteristics and styles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

FromJson

-0.55

 corred

-0.54

ThroughAttribute

-0.54

actionMode

-0.53

ActionButton

-0.53

openzeppelin

-0.52

ActionPerformed

-0.52

niaus

-0.51

GraphicsUnit

-0.50

 balance

-0.49

POSITIVE LOGITS

 hair

1.06

 hairstyles

1.05

 hairstyle

1.05

 hairst

1.00

 HAIR

0.99

 Hair

0.98

Hair

0.94

 hairdresser

0.93

 haircut

0.90

 haircuts

0.87

Activations Density 0.115%

descriptive terms related to hair characteristics and styles

No Comments

No Known Activations