INDEX

Explanations

descriptors that indicate positive attributes or qualities related to people, behavior, and experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 épaules

-0.67

 lèvres

-0.65

 enfans

-0.62

 dieux

-0.59

 Grecs

-0.58

 présentés

-0.58

iniest

-0.57

 genoux

-0.56

getRuntime

-0.56

 cérami

-0.55

POSITIVE LOGITS

 amounts

0.89

Personensuche

0.75

 levels

0.70

+#+#

0.65

gameserver

0.64

 doses

0.63

 quantities

0.61

 proportions

0.60

amounts

0.60

 circumstances

0.59

Activations Density 0.748%

descriptors that indicate positive attributes or qualities related to people, behavior, and experiences

No Comments

No Known Activations