INDEX

Explanations

phrases or sentences where something or someone is the focus of discussion or investigation

oai_token-act-pair · gpt-3.5-turbo

topics that are being discussed or debated within various contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 uncond

-0.71

frog

-0.71

pload

-0.63

jp

-0.62

othe

-0.62

ppa

-0.61

gob

-0.60

auga

-0.59

apons

-0.59

mb

-0.58

POSITIVE LOGITS

ENTION

0.80

 ridicule

0.80

 conversation

0.73

ilyn

0.71

actionDate

0.70

 litigation

0.69

spection

0.68

international

0.65

 controversy

0.64

æĺ¯

0.64

Activations Density 0.111%

phrases or sentences where something or someone is the focus of discussion or investigation

topics that are being discussed or debated within various contexts

No Comments

No Known Activations