INDEX

Explanations

social media related terms, particularly focusing on the word "tweet."

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "tweet" and related contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

vantage

-0.66

undai

-0.65

iencies

-0.62

inav

-0.62

 Defin

-0.62

iHUD

-0.61

cised

-0.60

 clitor

-0.59

 Penet

-0.58

 Trials

-0.58

POSITIVE LOGITS

storms

1.30

storm

1.27

weet

0.97

"@

0.93

 retweet

0.93

Tweet

0.91

 hashtag

0.91

deck

0.90

 hasht

0.86

realDonaldTrump

0.84

Activations Density 0.031%

social media related terms, particularly focusing on the word "tweet."

occurrences of the word "tweet" and related contexts

No Comments

No Known Activations