INDEX

Explanations

positive adjectives and descriptors in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/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.15.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

InstanceState

-0.59

getClassLoader

-0.58

 scooters

-0.58

 ieri

-0.56

 huts

-0.55

 onItemClick

-0.55

sellors

-0.55

 rockers

-0.54

 puns

-0.54

ContextHolder

-0.54

POSITIVE LOGITS

 phenomenon

0.59

 thing

0.59

 result

0.58

 addition

0.56

PerformLayout

0.55

لينكات

0.54

 vain

0.53

 topic

0.52

 entity

0.52

Rüyada

0.51

Activations Density 0.400%

positive adjectives and descriptors in various contexts

No Comments

No Known Activations