INDEX

Explanations

instances of actions or events that have a significant impact or consequence

oai_token-act-pair · gpt-3.5-turbo

instances of the word "act" and its variations, particularly in contexts emphasizing actions or behaviors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 Parad

-0.75

nda

-0.74

 Galile

-0.65

lake

-0.63

castle

-0.61

 Plate

-0.61

 Dise

-0.60

 Mous

-0.60

hander

-0.60

 Stud

-0.59

POSITIVE LOGITS

ional

1.31

uary

1.30

uated

1.22

ivism

1.13

uation

1.10

uating

1.05

ivity

1.03

uate

1.02

ual

1.00

inic

1.00

Activations Density 0.022%

instances of actions or events that have a significant impact or consequence

instances of the word "act" and its variations, particularly in contexts emphasizing actions or behaviors

No Comments

No Known Activations