INDEX

Explanations

phrases related to curiosity and questioning

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

}{*}{

-0.86

setVerticalGroup

-0.79

extAlignment

-0.77

Personendaten

-0.75

libft

-0.68

 doInBackground

-0.67

/*

-0.66

 typelib

-0.63

parsedMessage

-0.61

 forKey

-0.57

POSITIVE LOGITS

 wonder

0.74

 wonders

0.68

难怪

0.62

Wonder

0.59

 Wonder

0.58

wonder

0.57

jalá

0.56

 WONDER

0.56

 amazed

0.56

 irony

0.55

Activations Density 0.299%

phrases related to curiosity and questioning

No Comments

No Known Activations

phrases related to curiosity and questioning

No Comments

No Known Activations