INDEX

Explanations

programming code, identifiers of legal documents, person/organization involved in court cases and meta commentary written by website owner in interactive posts which include references to "us" and "we".

oai_token-act-pair · gemini-2.0-flash

First person

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

ſelves

-0.93

ſelf

-0.92

 depositphotos

-0.83

::=

-0.78

Efq

-0.75

 itſelf

-0.75

 Jefus

-0.75

 Majefty

-0.73

помним

-0.71

 ſind

-0.70

POSITIVE LOGITS

my

3.00

me

2.41

2.39

 myself

2.20

my

2.09

 tôi

2.06

 mijn

2.02

 meines

1.99

 saya

1.98

私は

1.98

Activations Density 20.132%

programming code, identifiers of legal documents, person/organization involved in court cases and meta commentary written by website owner in interactive posts which include references to "us" and "we".

First person

No Comments

No Known Activations

programming code, identifiers of legal documents, person/organization involved in court cases and meta commentary written by website owner in interactive posts which include references to "us" and "we".

First person

No Comments

No Known Activations