INDEX

Explanations

numbers and numerical patterns

oai_token-act-pair · gpt-3.5-turbo

references to time intervals and events

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

</

-0.78

ðŁĳ

-0.74

î

-0.70

 abroad

-0.69

-0.67

 elsewhere

-0.67

ãĢ

-0.67

\)

-0.66

Picture

-0.66

~~~~

-0.66

POSITIVE LOGITS

 approvals

0.56

 condemnation

0.56

 Apostle

0.52

 Earthquake

0.51

rontal

0.51

 Nero

0.51

 complicity

0.50

 Deborah

0.49

bestos

0.49

 condem

0.48

Activations Density 0.700%

numbers and numerical patterns

references to time intervals and events

No Comments

No Known Activations