INDEX

Explanations

phrases that indicate emotional or subjective experiences

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

 definately

-0.66

 consultato

-0.63

 idéia

-0.61

 callBack

-0.60

 muß

-0.60

<<-

-0.57

 poichè

-0.54

CallBack

-0.53

 '".$

-0.53

 المعيارى

-0.51

POSITIVE LOGITS

StoryboardSegue

0.76

 Numerade

0.61

nocześnie

0.59

 meaningfully

0.58

 weirdly

0.58

BitmapFactory

0.57

 NSCoder

0.56

—

0.55

Viitteet

0.54

⊗

0.53

Activations Density 0.516%

phrases that indicate emotional or subjective experiences

No Comments

No Known Activations