INDEX

Explanations

terms related to encryption and security keys, as well as specific phrases mentioning key-related actions

oai_token-act-pair · gpt-3.5-turbo

references to encryption and security keys

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

¬¼

-0.73

asma

-0.71

 Chatt

-0.70

ews

-0.70

 PHOTO

-0.65

ATIONAL

-0.64

Fif

-0.64

ļé

-0.64

asca

-0.63

ADRA

-0.63

POSITIVE LOGITS

stroke

1.42

*/(

1.12

bind

1.10

caps

1.08

chain

1.07

binding

1.06

stro

1.03

stone

1.01

ring

0.99

pad

0.99

Activations Density 0.033%

terms related to encryption and security keys, as well as specific phrases mentioning key-related actions

references to encryption and security keys

No Comments

No Known Activations