INDEX

Explanations

discussion of state or government funding

oai_token-act-pair · gemini-2.0-flash

terms related to authorization or funding processes

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

has

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

 وتسجيلات

-0.82

 للاسماء

-0.80

Personensuche

-0.79

bootstrapcdn

-0.74

contentLoaded

-0.73

tagHelperRunner

-0.69

httphttps

-0.69

ftagPool

-0.69

ⓧ

-0.68

 الرياضيه

-0.66

POSITIVE LOGITS

 réfé

0.50

 redire

0.47

ioutil

0.47

authorize

0.46

ANTIC

0.46

HEIM

0.45

solicit

0.45

 authorize

0.44

 Solicit

0.44

otka

0.44

Activations Density 2.456%

discussion of state or government funding

terms related to authorization or funding processes

has

No Comments

No Known Activations