INDEX

Explanations

phrases indicating time spans

oai_token-act-pair · gpt-3.5-turbo

phrases indicating time periods or ranges

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

Eye

-0.74

Planet

-0.73

YL

-0.67

 Deity

-0.66

Optional

-0.65

Ĩ

-0.63

ĵ

-0.62

Secondly

-0.61

Monster

-0.61

Required

-0.61

POSITIVE LOGITS

1.31

1.28

1.27

1.24

1.23

1.22

1.20

1.19

1.17

Activations Density 0.059%

phrases indicating time spans

phrases indicating time periods or ranges

No Comments

No Known Activations