INDEX

Explanations

keywords related to computer programming or code.<br>

oai_token-act-pair · gpt-3.5-turbo

the letter 'C' in a variety of contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Magikarp

-0.75

hof

-0.74

ãĥĦ

-0.73

 Tinder

-0.69

 Yamaha

-0.69

 absor

-0.68

ItemTracker

-0.67

 milit

-0.63

 Wrestle

-0.62

EStream

-0.62

POSITIVE LOGITS

overed

1.15

URRENT

1.09

olly

1.09

argo

1.07

ancel

1.05

isco

1.04

ursor

1.03

ollo

1.03

urses

1.02

rouch

1.02

Activations Density 0.048%

keywords related to computer programming or code.<br>

the letter 'C' in a variety of contexts

No Comments

No Known Activations