INDEX

Explanations

references to the latest version, technology, and updates

oai_token-act-pair · gpt-3.5-turbo

references to current technology and updates

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.10.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

terness

-0.86

onds

-0.85

pherd

-0.81

 teasp

-0.81

pathy

-0.77

uty

-0.76

ateral

-0.74

determination

-0.74

andering

-0.73

agram

-0.72

POSITIVE LOGITS

 versions

1.35

 iteration

1.30

 incarnation

1.21

 editions

1.17

 iterations

1.16

 technologies

1.16

 version

1.14

 additions

1.12

 advancements

1.11

 developments

1.09

Activations Density 0.082%

references to the latest version, technology, and updates

references to current technology and updates

No Comments

No Known Activations