INDEX

Explanations

phrases related to complex interconnections and relationships

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

ptroller

-0.90

iren

-0.80

claimer

-0.80

utenant

-0.79

assador

-0.78

OIL

-0.77

Hunt

-0.76

rection

-0.76

pter

-0.76

iologist

-0.76

POSITIVE LOGITS

 strands

1.28

 entities

1.24

 pieces

1.22

 layers

1.19

 groups

1.18

 branches

1.15

 components

1.12

 spheres

1.12

 generations

1.11

 universes

1.10

Activations Density 0.097%

phrases related to complex interconnections and relationships

No Comments

No Known Activations