INDEX

Explanations

forum posts or user profiles with information on the joining date and number of posts

oai_token-act-pair · gpt-3.5-turbo

references to the number of posts made by users

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 Bhar

-0.82

 Palest

-0.72

pled

-0.70

bill

-0.67

wyn

-0.63

 Brill

-0.63

fell

-0.62

bid

-0.62

blers

-0.62

SpaceEngineers

-0.62

POSITIVE LOGITS

 Posts

1.04

 Joined

1.00

ertodd

0.97

reply

0.75

greSQL

0.73

 Offense

0.73

 Awesome

0.73

ategory

0.72

 posts

0.72

Thread

0.71

Activations Density 0.010%

forum posts or user profiles with information on the joining date and number of posts

references to the number of posts made by users

No Comments

No Known Activations