INDEX

Explanations

phrases indicating direction or movement

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

omaly

-0.88

etheless

-0.78

 cautiously

-0.71

amar

-0.70

terday

-0.69

Chance

-0.64

little

-0.64

fortunately

-0.64

also

-0.63

 nonetheless

-0.63

POSITIVE LOGITS

 Manufacturer

0.65

ierrez

0.63

 Github

0.62

achable

0.61

OURCE

0.60

 consumers

0.60

ledged

0.59

SpaceEngineers

0.59

Gov

0.59

orsi

0.58

Activations Density 0.076%

phrases indicating direction or movement

No Comments

No Known Activations