INDEX

Explanations

various types of dresses and skirts

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

dresses or skirts

np_acts-logits-general · gemini-2.0-flash

dress and skirt

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

TM

-0.34

 puncture

-0.33

blick

-0.33

 Langley

-0.32

bit

-0.31

 micro

-0.31

oni

-0.31

bic

-0.31

穴

-0.30

мки

-0.30

POSITIVE LOGITS

 dress

1.10

 dresses

1.09

dress

1.00

 DRESS

0.98

 skirt

0.96

 skirts

0.95

 Dresses

0.92

 Dress

0.92

Dress

0.91

 Skirt

0.86

Activations Density 0.228%

various types of dresses and skirts

dresses or skirts

dress and skirt

No Comments

No Known Activations