INDEX

Explanations

calls to action related to subscribing to newsletters

oai_token-act-pair · gpt-3.5-turbo

instances of the word "subscribe."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

mong

-0.77

esan

-0.69

put

-0.69

ilde

-0.66

ball

-0.63

comes

-0.63

 curv

-0.62

 stride

-0.61

 vengeance

-0.60

scape

-0.59

POSITIVE LOGITS

Subscribe

1.05

 Subscribe

0.95

 Emails

0.94

éĹĺ

0.89

Alert

0.88

ables

0.82

Spons

0.81

 Email

0.77

isodes

0.76

ĨĴ

0.76

Activations Density 0.010%

calls to action related to subscribing to newsletters

instances of the word "subscribe."

No Comments

No Known Activations