INDEX

Explanations

instances of the word "consent" and phrases that include the word "consent."

oai_token-act-pair · gemini-2.0-flash

consent

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 doubtnut

-0.91

 مرئيه

-0.87

 myſelf

-0.87

ourites

-0.84

 InputDecoration

-0.82

 reCAPTCHA

-0.82

findpost

-0.81

Hochspringen

-0.80

olerance

-0.80

UnsafeEnabled

-0.80

POSITIVE LOGITS

0.69

0.64

...

0.63

<eos>

0.61

ingen

0.57

…

0.57

or

0.56

Activations Density 1.562%

instances of the word "consent" and phrases that include the word "consent."

consent

No Comments

No Known Activations