INDEX

Explanations

emotions and mental states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

<bos>

-0.65

 Competence

-0.49

hagy

-0.46

 amperes

-0.46

ExecuteReader

-0.44

 ASSERT

-0.43

ProductService

-0.42

(',');

-0.42

 ProductService

-0.41

gale

-0.41

POSITIVE LOGITS

 easily

0.82

easily

0.77

 Easily

0.70

Easily

0.68

 fragility

0.67

 sensitivity

0.66

 responding

0.64

 sensitive

0.63

 susceptibility

0.62

 fright

0.60

Activations Density 0.271%

emotions and mental states

No Comments

No Known Activations