INDEX

Explanations

references to specific points in time or instances of events happening

oai_token-act-pair · gpt-3.5-turbo

mentions of significant historical events or milestones

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

ords

-0.65

 meantime

-0.64

 ILCS

-0.63

 Attribution

-0.57

 Extension

-0.56

 Journals

-0.56

 abound

-0.55

olor

-0.54

modules

-0.54

 priceless

-0.54

POSITIVE LOGITS

 ever

1.28

 EVER

1.26

 ventured

1.12

 interacted

1.12

 bothered

1.07

ever

1.03

 visited

1.01

 interfered

1.00

 encountered

0.96

 dared

0.96

Activations Density 0.133%

references to specific points in time or instances of events happening

mentions of significant historical events or milestones

No Comments

No Known Activations