INDEX

Explanations

concepts related to concealment or deception

oai_token-act-pair · gpt-3.5-turbo

words related to deception and concealment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

•Weird neurons

No Comments

Negative Logits

 stead

-0.64

 Tale

-0.64

culosis

-0.63

 Bucks

-0.62

 smack

-0.62

FOX

-0.61

Dug

-0.61

Yor

-0.60

 nights

-0.60

 Wheels

-0.59

POSITIVE LOGITS

ivably

1.95

iving

1.40

ivable

1.38

ives

1.19

veland

1.15

ipt

1.14

ivers

1.10

mble

1.09

ibly

1.05

aling

1.05

Activations Density 0.058%

concepts related to concealment or deception

words related to deception and concealment

No Comments

No Known Activations