INDEX

Explanations

information related to research studies and their authors

oai_token-act-pair · gpt-3.5-turbo

citations of academic studies and their authors

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

 ballot

-0.73

DonaldTrump

-0.72

 lockout

-0.72

 franch

-0.71

aepernick

-0.70

illion

-0.70

Exit

-0.69

Premium

-0.69

TRUMP

-0.69

netflix

-0.67

POSITIVE LOGITS

 researchers

1.48

 doctoral

1.40

 collaborators

1.37

 scientists

1.33

 researcher

1.32

 physicists

1.30

 colleagues

1.28

 Researchers

1.22

PhD

1.20

Researchers

1.20

Activations Density 0.356%

information related to research studies and their authors

citations of academic studies and their authors

No Comments

No Known Activations