INDEX

Explanations

phrases related to returning to a previous state or condition

oai_token-act-pair · gpt-3.5-turbo

phrases indicating a return to a previous state or condition

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

few

-0.75

neys

-0.72

ghai

-0.65

ischer

-0.63

aughters

-0.63

ccoli

-0.62

bitious

-0.62

urst

-0.61

 divor

-0.60

 hoops

-0.60

POSITIVE LOGITS

 equilibrium

1.16

 normal

1.15

 optimum

1.09

normal

1.02

 pristine

1.02

 optimal

1.02

 rightful

0.95

 proper

0.95

 norm

0.91

Normal

0.91

Activations Density 0.285%

phrases related to returning to a previous state or condition

phrases indicating a return to a previous state or condition

No Comments

No Known Activations