INDEX

Explanations

proper nouns specifically related to individuals, potentially with a focus on names starting with "R" and "A"

oai_token-act-pair · gpt-3.5-turbo

references to specific individuals, particularly those with the name "Richie" or "Aber."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

itar

-0.88

oran

-0.85

imer

-0.81

oting

-0.80

ivity

-0.80

istics

-0.78

urally

-0.76

oros

-0.76

ennis

-0.76

IPS

-0.75

POSITIVE LOGITS

lain

0.81

xus

0.80

Downloadha

0.74

utical

0.74

 Inher

0.73

 Aber

0.72

 Flavoring

0.72

0.69

 Abbey

0.69

 Rough

0.68

Activations Density 0.023%

proper nouns specifically related to individuals, potentially with a focus on names starting with "R" and "A"

references to specific individuals, particularly those with the name "Richie" or "Aber."

No Comments

No Known Activations