INDEX

Explanations

technical terms, numbers, and statistical information

oai_token-act-pair · gpt-3.5-turbo

references to statistical data and its implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

bernatorial

-0.51

rium

-0.50

iatus

-0.50

-+-+

-0.49

different

-0.48

ratom

-0.47

():

-0.46

ggle

-0.46

 Siem

-0.46

ergy

-0.45

POSITIVE LOGITS

 notwithstanding

0.80

ãĥ³ãĤ¸

0.55

 comprom

0.53

 defends

0.53

 è£ıè

0.50

 thereof

0.50

 plat

0.48

 Nanto

0.48

 extraord

0.48

olver

0.46

Activations Density 1.740%

technical terms, numbers, and statistical information

references to statistical data and its implications

No Comments

No Known Activations