INDEX

Explanations

action-related words and numbers, especially related to steps or procedures

oai_token-act-pair · gpt-3.5-turbo

references to steps in a process or sequential actions

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

Negative Logits

DragonMagazine

-0.52

etheless

-0.42

 Canaver

-0.37

ãĥĺãĥ©

-0.36

ãĤ¼ãĤ¦ãĤ¹

-0.36

channelAvailability

-0.36

iannopoulos

-0.36

cedented

-0.35

unctions

-0.35

aterasu

-0.34

POSITIVE LOGITS

CAD

0.33

 droid

0.33

dyn

0.32

 [âĢ¦]

0.32

 [...]

0.31

 dynam

0.31

 elim

0.31

 enlarg

0.31

 choke

0.29

 indu

0.29

Activations Density 4.507%

action-related words and numbers, especially related to steps or procedures

references to steps in a process or sequential actions

No Known Activations