INDEX

Explanations

action-oriented phrases, particularly those involving the verb "take."

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

__":

-0.65

//

-0.65

__':

-0.65

伎

-0.65

はじめに

-0.64

__':

-0.63

__":

-0.55

 AssemblyTitle

-0.54

 Drapeau

-0.51

发表于

-0.50

POSITIVE LOGITS

 stock

0.71

 account

0.63

stock

0.59

 note

0.57

Stock

0.56

 cogniz

0.55

due

0.54

due

0.53

 Stock

0.52

orianCalendar

0.51

Activations Density 0.253%

action-oriented phrases, particularly those involving the verb "take."

No Comments

No Known Activations