INDEX

Explanations

social media accounts mentioned in the text

oai_token-act-pair · gpt-3.5-turbo

references to social media accounts, particularly Twitter and Facebook

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Bagg

-0.70

arate

-0.66

aito

-0.63

PDF

-0.62

hospital

-0.60

 defeat

-0.60

Aid

-0.60

 seams

-0.59

ãĥ©ãĥ³

-0.59

 anesthesia

-0.59

POSITIVE LOGITS

(@

0.99

 username

0.98

"@

0.92

0.91

www

0.86

 facebook

0.84

annels

0.79

/#

0.79

acebook

0.78

edin

0.77

Activations Density 0.156%

social media accounts mentioned in the text

references to social media accounts, particularly Twitter and Facebook

No Comments

No Known Activations