INDEX

Explanations

phrases related to invisibility or being hidden

oai_token-act-pair · gpt-3.5-turbo

concepts related to invisibility or things that are hidden from the general public

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

uesday

-0.60

FTWARE

-0.60

 hangs

-0.59

atto

-0.59

rice

-0.58

ornia

-0.58

 themed

-0.58

Krist

-0.57

BACK

-0.56

KA

-0.55

POSITIVE LOGITS

 mortals

1.20

 outsiders

1.12

 passers

1.00

 onlook

0.98

 anyone

0.95

 anybody

0.92

 humans

0.92

 civilized

0.91

 humankind

0.91

 mainstream

0.89

Activations Density 0.380%

phrases related to invisibility or being hidden

concepts related to invisibility or things that are hidden from the general public

No Comments

No Known Activations