INDEX

Explanations

phrases indicating changes or updates in status

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

é¾

-0.71

efe

-0.70

quickShipAvailable

-0.66

achev

-0.66

 privatization

-0.64

soType

-0.63

phen

-0.61

 attendance

-0.60

bent

-0.60

POSITIVE LOGITS

adays

1.29

 correctly

0.92

here

0.91

 properly

0.83

 reversible

0.80

 include

0.80

 accurately

0.78

 available

0.76

 fully

0.75

 reliably

0.75

Activations Density 0.037%

phrases indicating changes or updates in status

No Comments

No Known Activations