INDEX

Explanations

terms associated with loss or losing

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

 intptr

-0.63

 ویکی‌پدی

-0.60

 Roskov

-0.60

 cientí

-0.59

∭

-0.58

FieldNumber

-0.57

WireFormat

-0.56

@"/

-0.56

={`/

-0.54

 ThemeData

-0.54

POSITIVE LOGITS

 sight

0.86

 track

0.86

 faith

0.78

 control

0.77

 grip

0.77

 touch

0.73

 sleep

0.72

 momentum

0.72

 patience

0.70

 focus

0.69

Activations Density 0.176%

terms associated with loss or losing

No Comments

No Known Activations