INDEX

Explanations

references to different stages of childhood and adolescence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/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.21.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

 Cambrian

-0.55

Билгалдахарш

-0.51

válasz

-0.51

versaire

-0.51

 NUKAT

-0.49

Искәрмәләр

-0.49

fjspx

-0.48

 relegation

-0.48

 بيها

-0.48

 cdti

-0.47

POSITIVE LOGITS

 adult

2.96

 adults

2.88

adult

2.64

Adult

2.54

 Adult

2.53

 Adults

2.51

adults

2.46

 adulte

2.37

 ADULT

2.35

Adults

2.35

Activations Density 0.279%

references to different stages of childhood and adolescence

No Comments

No Known Activations