INDEX

Explanations

differences or contradictions in information presented

oai_token-act-pair · gpt-3.5-turbo

terms related to difference and diversity in perspectives or opinions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

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

ittee

-0.88

ulhu

-0.86

washer

-0.84

orah

-0.84

hander

-0.83

ften

-0.81

herer

-0.79

jam

-0.79

ptroller

-0.78

former

-0.78

POSITIVE LOGITS

 amounts

1.44

 levels

1.35

 outcomes

1.34

 responses

1.31

 situations

1.30

 views

1.30

 opinions

1.29

 visions

1.28

 quantities

1.27

 proportions

1.27

Activations Density 0.434%

differences or contradictions in information presented

terms related to difference and diversity in perspectives or opinions

No Comments

No Known Activations