INDEX

Explanations

the number "one" and words that go along with counting

oai_token-act-pair · gemini-2.0-flash

instances of the word 'one'

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

one

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

one

-1.19

one

-0.94

One

-0.85

 یکی

-0.82

 één

-0.79

ono

-0.78

 jednej

-0.77

 unul

-0.76

 один

-0.76

 یک

-0.74

POSITIVE LOGITS

or

0.81

 thing

0.79

WebElementEntity

0.71

twimg

0.60

 sola

0.57

 portion

0.54

rungsseite

0.54

 method

0.53

 person

0.51

 article

0.51

Activations Density 3.192%

the number "one" and words that go along with counting

instances of the word 'one'

one

No Comments

No Known Activations