INDEX

Explanations

references to invisibility, both literal and metaphorical

oai_token-act-pair · gpt-3.5-turbo

references to the concept of invisibility

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

andals

-0.89

ortment

-0.82

ership

-0.81

eda

-0.77

olitan

-0.76

ulet

-0.76

âķĲâķĲ

-0.76

aeper

-0.75

YC

-0.74

ocations

-0.74

POSITIVE LOGITS

 invisible

0.88

 invis

0.85

worm

0.83

immune

0.78

 phantom

0.77

 Invisible

0.77

 glove

0.71

worms

0.70

 Coffin

0.69

Lap

0.69

Activations Density 0.037%

references to invisibility, both literal and metaphorical

references to the concept of invisibility

No Comments

No Known Activations