INDEX

Explanations

terms related to cosmology and the universe

oai_token-act-pair · gpt-3.5-turbo

references to the universe

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

espie

-0.80

urers

-0.70

ancing

-0.70

ippi

-0.69

rib

-0.69

thodox

-0.67

dm

-0.62

iffs

-0.62

IFF

-0.62

ients

-0.62

POSITIVE LOGITS

eers

1.05

arium

1.03

entric

0.83

ALLY

0.81

wide

0.80

 collide

0.79

naire

0.77

frey

0.77

 Tsukuyomi

0.73

ulously

0.70

Activations Density 0.023%

terms related to cosmology and the universe

references to the universe

No Comments

No Known Activations