INDEX

Explanations

actions related to closing and securing objects or spaces

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 ujednoznacz

-0.93

SourceChecksum

-0.67

]--;

-0.67

 digress

-0.66

 gynhyrchwyd

-0.65

 فريبيس

-0.64

ToDelete

-0.61

WithIOException

-0.60

 Constantin

-0.59

ardless

-0.58

POSITIVE LOGITS

 closing

0.70

 closure

0.58

 closes

0.57

Closing

0.56

Closure

0.55

 penutup

0.55

 Closure

0.54

 closed

0.54

 Closing

0.52

 menutup

0.51

Activations Density 0.240%

actions related to closing and securing objects or spaces

No Comments

No Known Activations