INDEX

Explanations

terms related to spatial and temporal awareness

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

ortium

-0.85

doms

-0.83

vous

-0.81

uberty

-0.76

gg

-0.75

ardless

-0.73

udder

-0.73

akura

-0.72

qt

-0.72

EGA

-0.72

POSITIVE LOGITS

ities

1.11

 spatial

0.96

 lobe

0.94

 distortions

0.94

 cognition

0.93

ity

0.92

 coordinates

0.91

 anomalies

0.89

 dimensions

0.88

 accuracy

0.88

Activations Density 0.010%

terms related to spatial and temporal awareness

No Comments

No Known Activations