INDEX

Explanations

words related to performances and names

oai_token-act-pair · gemini-2.0-flash

performances/organizations

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

IntoConstraints

-0.73

scrapy

-0.72

nables

-0.70

pulumi

-0.69

leeve

-0.63

InSection

-0.63

Portale

-0.62

UserScript

-0.60

stuffs

-0.59

ніципалі

-0.57

POSITIVE LOGITS

 dance

1.41

 dances

1.27

 Dance

1.26

 dancers

1.25

 danced

1.19

Dance

1.19

 dancing

1.16

 DANCE

1.09

 dancer

1.07

dance

1.07

Activations Density 0.539%

words related to performances and names

performances/organizations

No Comments

No Known Activations