INDEX

Explanations

mentions of a central location or focal point

oai_token-act-pair · gpt-3.5-turbo

frequent mentions of the term "hub" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

ittee

-0.82

IGHTS

-0.80

DonaldTrump

-0.75

veyard

-0.74

essee

-0.74

avery

-0.69

ippery

-0.66

 Jackets

-0.64

 manuscripts

-0.64

vironment

-0.63

POSITIVE LOGITS

hub

1.55

hub

1.24

 hubs

1.23

bub

1.18

Hub

1.14

Hub

1.10

bard

1.02

caps

0.82

rod

0.80

lov

0.79

Activations Density 0.006%

mentions of a central location or focal point

frequent mentions of the term "hub" in various contexts

No Comments

No Known Activations