INDEX

Explanations

words related to technical features or functions

oai_token-act-pair · gpt-3.5-turbo

phrases that introduce or reference specific attributes or functions associated with items

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

ourcing

-0.74

ODY

-0.71

etheless

-0.66

igated

-0.65

icipated

-0.64

artisan

-0.61

rafted

-0.61

ION

-0.61

oubted

-0.60

aukee

-0.60

POSITIVE LOGITS

 accompanies

1.39

 governs

1.39

 allows

1.36

 regulates

1.34

 attaches

1.33

 directs

1.31

 activates

1.30

 determines

1.29

 enables

1.29

 lets

1.28

Activations Density 0.165%

words related to technical features or functions

phrases that introduce or reference specific attributes or functions associated with items

No Comments

No Known Activations