INDEX

Explanations

hashtags on Twitter

oai_token-act-pair · gpt-3.5-turbo

references to hashtags and trending topics on social media

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

kus

-0.85

oun

-0.75

undai

-0.72

ateral

-0.72

odcast

-0.71

 destro

-0.69

eln

-0.69

llah

-0.68

 contracting

-0.63

quartered

-0.63

POSITIVE LOGITS

 hashtag

1.22

 hasht

1.11

tags

1.06

"#

1.02

="#

0.95

âĢİ

0.87

=""

0.85

(#

0.79

username

0.78

netflix

0.76

Activations Density 0.015%

hashtags on Twitter

references to hashtags and trending topics on social media

No Comments

No Known Activations