INDEX

Explanations

references to legal concepts and terminology related to restraint and control

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs49152-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

torch.float32

Hook Point

blocks.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãĥĥãĥī

-0.79

 seiz

-0.70

adobe

-0.64

ename

-0.63

 looph

-0.62

canon

-0.62

Osw

-0.62

ãĥ´ãĤ¡

-0.61

and

-0.59

 TODAY

-0.59

POSITIVE LOGITS

 alike

1.54

 respectively

1.45

 versa

0.85

 technologies

0.81

 setups

0.81

 environments

0.80

 scenarios

0.78

 collide

0.78

 systems

0.77

 modes

0.77

Activations Density 0.266%

references to legal concepts and terminology related to restraint and control

No Comments

No Known Activations