INDEX

Explanations

technical terms related to data analysis and technology

oai_token-act-pair · gpt-3.5-turbo

terms related to digital and data-driven technologies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.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

 Ital

-0.74

 laure

-0.72

 Ambrose

-0.66

 Kenny

-0.65

 Reward

-0.65

 Chiefs

-0.65

 Norris

-0.64

Ki

-0.64

 Caucasus

-0.63

Kag

-0.62

POSITIVE LOGITS

based

1.38

driven

1.28

mediated

1.23

centric

1.21

enabled

1.14

generated

1.10

operated

1.10

derived

1.10

processing

1.08

induced

1.08

Activations Density 0.103%

technical terms related to data analysis and technology

terms related to digital and data-driven technologies

No Comments

No Known Activations