INDEX

Explanations

references to possessive pronouns, particularly "own."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 avoient

-0.79

 étoient

-0.72

出版年

-0.67

 navideño

-0.67

 Protestants

-0.67

 étoit

-0.67

 auroit

-0.64

 cherries

-0.64

 involucrados

-0.63

 vectorielle

-0.62

POSITIVE LOGITS

own

2.66

Own

2.20

Own

2.04

own

1.89

OWN

1.87

 eigenen

1.66

 sendiri

1.59

 eigenes

1.54

 eigene

1.51

 propia

1.48

Activations Density 0.046%

references to possessive pronouns, particularly "own."

No Comments

No Known Activations