INDEX

Explanations

the word "We" and related forms, indicating a focus on collective or shared experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 Thon

-0.77

Chy

-0.77

WithIOException

-0.75

Chy

-0.69

 pathlib

-0.65

 Salat

-0.64

 Padang

-0.64

 fior

-0.63

 Monfieur

-0.62

 Ueber

-0.62

POSITIVE LOGITS

We

1.66

We

1.61

we

1.57

we

1.38

WE

1.20

 ourselves

1.16

Мы

1.13

 Мы

1.10

 Weinstein

1.04

WE

1.04

Activations Density 0.189%

the word "We" and related forms, indicating a focus on collective or shared experiences

No Comments

No Known Activations