INDEX

Explanations

descriptors of positive qualities and attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 الحره

-0.79

 ")");

-0.75

 ModelExpression

-0.70

apimachinery

-0.69

Identyfik

-0.65

eraard

-0.64

PMailer

-0.64

adget

-0.63

 كومونز

-0.60

✨:

-0.60

POSITIVE LOGITS

 reliable

1.03

 powerful

1.01

 comfortable

0.96

 dependable

0.96

 efficient

0.95

 beautiful

0.93

 attractive

0.93

 vibrant

0.91

 accurate

0.91

 sturdy

0.89

Activations Density 0.323%

descriptors of positive qualities and attributes

No Comments

No Known Activations