INDEX

Explanations

phrases related to the brand "Land Rover."

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

 Qiao

-0.67

hift

-0.67

Eps

-0.65

utic

-0.64

aukee

-0.63

 Universe

-0.61

BILITY

-0.61

 Fior

-0.61

 Braz

-0.60

BILITIES

-0.60

POSITIVE LOGITS

scape

1.32

marks

1.16

lord

1.14

lords

1.14

mine

1.13

mark

1.13

locked

1.09

fill

1.06

gra

1.04

owner

1.01

Activations Density 0.029%

phrases related to the brand "Land Rover."

No Comments

No Known Activations