INDEX

Explanations

the word "Em" followed by a number, potentially related to emotions

oai_token-act-pair · gpt-3.5-turbo

references to the term "Emory."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

 Kubrick

-0.80

 sund

-0.70

aird

-0.69

Lago

-0.68

Downloadha

-0.67

ASC

-0.65

 Manitoba

-0.64

WAYS

-0.64

 Alberta

-0.63

YPG

-0.63

POSITIVE LOGITS

otions

1.15

igrants

1.15

igrant

1.13

otional

1.12

phasis

1.10

otion

1.10

brace

1.04

blems

1.03

perors

1.02

eme

1.02

Activations Density 0.004%

the word "Em" followed by a number, potentially related to emotions

references to the term "Emory."

No Comments

No Known Activations