INDEX

Explanations

terms related to the concept of invisibility

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 @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

aeper

-0.85

âķĲâķĲ

-0.85

anchester

-0.82

xit

-0.80

Interstitial

-0.79

ership

-0.78

olitan

-0.74

sych

-0.74

ulet

-0.73

ortment

-0.72

POSITIVE LOGITS

knife

0.76

 invisible

0.75

 invis

0.75

 phantom

0.74

worms

0.73

 silhou

0.70

worm

0.70

ibility

0.67

 Invisible

0.67

ink

0.66

Activations Density 0.060%

terms related to the concept of invisibility

references to the concept of invisibility

No Known Activations