INDEX

Explanations

words associated with a sequence of actions or events, particularly those that involve movement or change of state, and often include time-related terms.

oai_token-act-pair · gemini-2.0-flash

movement or transport

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

 betweenstory

-0.71

ReusableCell

-0.69

oa̍t

-0.63

 ویکی‌پدیا

-0.59

зулта

-0.58

\{\\

-0.57

.)}

-0.55

rungsseite

-0.54

ConstraintMaker

-0.54

}$}

-0.54

POSITIVE LOGITS

FormTagHelper

0.59

without

0.59

UNTAS

0.54

 without

0.52

 WITHOUT

0.49

CWE

0.48

reactivex

0.48

TagHelpers

0.47

adata

0.46

via

0.46

Activations Density 2.538%

words associated with a sequence of actions or events, particularly those that involve movement or change of state, and often include time-related terms.

movement or transport

No Comments

No Known Activations