INDEX

Explanations

phrases and terms related to social and cultural commentary

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

Datuak

-0.79

 disambiguazione

-0.69

 Normdatei

-0.66

 Some

-0.63

 tertentu

-0.60

Some

-0.58

 OFDb

-0.58

خرى

-0.56

 Sometimes

-0.55

 Algunos

-0.55

POSITIVE LOGITS

 every

3.41

every

2.84

 EVERY

2.52

EVERY

2.48

 everything

2.40

Every

2.31

 Every

2.26

everything

2.07

 EVERYTHING

2.01

 everyone

1.96

Activations Density 1.160%

phrases and terms related to social and cultural commentary

No Comments

No Known Activations