INDEX

Explanations

internet usernames/identifiers

oai_token-act-pair · gpt-3.5-turbo

elements related to online communication or social media interactions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Ghostbusters

-0.63

 worms

-0.61

 Wizards

-0.61

 Mono

-0.60

Tee

-0.57

 Skyrim

-0.57

 accomplished

-0.57

 plank

-0.55

 Mormons

-0.55

 Hydra

-0.54

POSITIVE LOGITS

 WATCHED

0.81

yss

0.80

ABC

0.80

 PHOTO

0.72

 SHARES

0.72

htaking

0.71

='

0.70

azeera

0.69

allery

0.69

CBC

0.69

Activations Density 0.504%

internet usernames/identifiers

elements related to online communication or social media interactions

No Comments

No Known Activations