INDEX

Explanations

words and phrases related to the presence or availability of information in a process

oai_token-act-pair · gemini-2.0-flash

terms indicating requests for information

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

information/evidence

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

 much

-1.30

 amount

-1.18

 mucho

-1.03

amount

-0.96

 lots

-0.95

much

-0.95

 Much

-0.94

 amounts

-0.93

 Amount

-0.90

Much

-0.90

POSITIVE LOGITS

Obrázky

0.75

OGND

0.68

AndEndTag

0.65

ⓧ

0.65

 дописавши

0.63

TargetException

0.61

audiovisuel

0.59

 gainera

0.59

SequentialGroup

0.59

 SEDS

0.58

Activations Density 2.851%

words and phrases related to the presence or availability of information in a process

terms indicating requests for information

information/evidence

No Comments

No Known Activations