INDEX

Explanations

phrases related to tasks, projects, and work

oai_token-act-pair · gpt-3.5-turbo

references to various tasks, responsibilities, or actions

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

ropy

-0.68

igion

-0.67

 Citation

-0.64

 ç¥ŀ

-0.64

WAYS

-0.64

eret

-0.63

entimes

-0.62

 Racial

-0.62

nor

-0.62

Benz

-0.62

POSITIVE LOGITS

 lined

1.28

 awaiting

1.27

 underway

1.19

 unfinished

1.17

 waiting

1.14

 ready

1.11

 looming

1.11

 planned

1.11

 coming

1.03

 pending

1.02

Activations Density 0.292%

phrases related to tasks, projects, and work

references to various tasks, responsibilities, or actions

No Comments

No Known Activations