INDEX

Explanations

sentences that express a proposition or a state of being by tokenizing on the word 'is', sometimes with a few content words around it

oai_token-act-pair · gemini-2.0-flash

is are

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

__

-0.42

中

-0.41

We

-0.38

Per

-0.38

we

-0.37

it

-0.36

RepeatedField

-0.36

POSITIVE LOGITS

SharedCtor

0.85

 EconPapers

0.82

 للاسماء

0.78

oa̍t

0.77

 CreateTagHelper

0.76

]--;

0.73

/>";

0.72

EndGlobalSection

0.71

StoryboardSegue

0.70

yarnpkg

0.69

Activations Density 1.525%

sentences that express a proposition or a state of being by tokenizing on the word 'is', sometimes with a few content words around it

is are

No Comments

No Known Activations