INDEX

Explanations

key terms related to advertising or editorial content

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 princ

-0.96

 advoc

-0.87

 unsus

-0.85

 tram

-0.84

 hospitality

-0.80

 unconditional

-0.79

 barr

-0.79

 petrol

-0.78

 friendly

-0.78

 conscious

-0.77

POSITIVE LOGITS

Advertisement

1.48

RELATED

1.43

Though

1.32

advertisement

1.32

According

1.31

However

1.28

Interestingly

1.28

Others

1.26

That

1.26

Other

1.25

Activations Density 0.051%

key terms related to advertising or editorial content

No Comments

No Known Activations