INDEX

Explanations

the words in, out, there, or this.

oai_token-act-pair · gemini-2.0-flash

phrases indicating location or presence

np_token-act-pair-logits · gpt-4o-mini

variations of "here"

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

ValueStyle

-0.68

 وتسجيلات

-0.68

ⓧ

-0.66

astify

-0.59

tonode

-0.58

 disambiguazione

-0.57

Westfalen

-0.57

contentLoaded

-0.56

檚

-0.55

oneta

-0.52

POSITIVE LOGITS

 here

3.22

here

2.41

 aquí

2.28

 Here

2.14

 aqui

2.13

 здесь

2.13

Here

2.09

 HERE

2.06

 aici

2.02

ici

1.98

Activations Density 1.638%

the words in, out, there, or this.

phrases indicating location or presence

variations of "here"

No Comments

No Known Activations

the words in, out, there, or this.

phrases indicating location or presence

variations of "here"

No Comments

No Known Activations