INDEX

Explanations

phrases related to shared experiences and collaboration

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

the word "together"

np_acts-logits-general · gemini-2.0-flash

activities done together

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 насељу

-0.48

orr

-0.42

InputElement

-0.41

 հղումներ

-0.41

owano

-0.39

farande

-0.39

jenner

-0.38

 πλη

-0.38

 contacter

-0.37

 skak

-0.37

POSITIVE LOGITS

 together

3.11

 Together

2.70

together

2.69

Together

2.64

 juntos

2.50

 TOGETHER

2.45

 jointly

2.09

gether

2.02

 gemeinsam

2.01

 collectively

1.83

Activations Density 0.296%

phrases related to shared experiences and collaboration

the word "together"

activities done together

No Comments

No Known Activations