INDEX

Explanations

references to emotional states and experiences

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

figer

-0.58

 équ

-0.57

ظيم

-0.56

oneofs

-0.55

 marav

-0.54

сшта

-0.53

 Valenzuela

-0.53

soe

-0.53

mij

-0.53

++)

-0.52

POSITIVE LOGITS

 acids

0.95

Emotional

0.93

 Emotional

0.91

 emotional

0.89

emotional

0.82

 Acid

0.77

 ACID

0.77

 tape

0.77

tape

0.76

 Acids

0.76

Activations Density 0.042%

references to emotional states and experiences

No Comments

No Known Activations