INDEX

Explanations

proper nouns, particularly names of individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

 herself

-0.85

 hostess

-0.75

 Maryam

-0.74

 Aphrodite

-0.73

 Mariam

-0.71

 Beatriz

-0.69

 goddess

-0.68

 purpoſe

-0.68

 auroit

-0.67

 zelve

-0.67

POSITIVE LOGITS

 himself

0.80

 Michael

0.64

himself

0.63

 John

0.63

Jr

0.62

 dapper

0.60

 prostate

0.59

 David

0.58

 Himself

0.57

 Timothy

0.56

Activations Density 0.551%

proper nouns, particularly names of individuals

No Comments

No Known Activations