INDEX

Explanations

technical terms related to data centers and processors

oai_token-act-pair · gpt-3.5-turbo

occurrences of the term "data" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 Flavoring

-0.80

 Clive

-0.79

 Nile

-0.77

 Safety

-0.76

 Irwin

-0.74

 Fisher

-0.73

Pul

-0.73

 Stoke

-0.70

rir

-0.70

 Salman

-0.69

POSITIVE LOGITS

dat

3.38

ta

1.43

tha

1.19

 hiber

1.18

dat

1.15

mah

1.03

yo

1.02

 servers

0.95

dur

0.95

 somet

0.94

Activations Density 0.014%

technical terms related to data centers and processors

occurrences of the term "data" and its variations

No Comments

No Known Activations