INDEX

Explanations

terms associated with data tracking and surveillance practices

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

ndra

-0.86

ghai

-0.79

awar

-0.79

stall

-0.77

swick

-0.77

ggle

-0.73

ntil

-0.73

enegger

-0.72

================================================================

-0.72

uden

-0.71

POSITIVE LOGITS

adata

0.94

 metadata

0.92

 dumps

0.82

 extracted

0.81

 databases

0.79

 collected

0.78

 trove

0.78

 retrieval

0.77

 files

0.76

metadata

0.76

Activations Density 0.010%

terms associated with data tracking and surveillance practices

No Comments

No Known Activations