INDEX

Explanations

mentions of family or familial relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 Sephora

-0.55

jsonwebtoken

-0.55

 JpaRepository

-0.54

 OnInit

-0.53

endios

-0.50

 Cosmetics

-0.49

 disbur

-0.48

 Lexicon

-0.47

 indict

-0.47

opus

-0.47

POSITIVE LOGITS

 family

4.77

family

4.19

 Family

4.03

Family

3.95

 FAMILY

3.81

FAMILY

3.47

 families

3.10

 famille

3.06

 familia

2.94

 famiglia

2.90

Activations Density 0.079%

mentions of family or familial relationships

No Comments

No Known Activations