INDEX

Explanations

phrases related to durations of time

oai_token-act-pair · gpt-3.5-turbo

phrases indicating duration or periods of time

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

thood

-0.78

orthy

-0.77

 Benef

-0.75

Soc

-0.75

acea

-0.74

omever

-0.72

Percent

-0.69

 redeem

-0.68

identally

-0.68

reci

-0.67

POSITIVE LOGITS

 delays

1.37

 deliberations

1.28

 deliber

1.26

 agon

1.22

 negotiations

1.21

 limbo

1.20

wr

1.19

 frantic

1.16

 bureaucratic

1.15

 negotiation

1.15

Activations Density 0.400%

phrases related to durations of time

phrases indicating duration or periods of time

No Comments

No Known Activations