INDEX

Explanations

terms related to legal violations and patent infringement

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 dreamstime

-0.78

 تانيه

-0.78

 Bowles

-0.74

 Bals

-0.72

AxisAlignment

-0.71

 doubtnut

-0.70

 Holtz

-0.70

 Monfieur

-0.70

 poffible

-0.69

 Glaser

-0.68

POSITIVE LOGITS

 infringement

1.09

 infringe

1.05

ringed

0.81

ringing

0.75

ringes

0.73

ftagPool

0.66

openzeppelin

0.63

Inf

0.61

ringe

0.60

ορ

0.59

Activations Density 0.001%

terms related to legal violations and patent infringement

No Comments

No Known Activations