INDEX

Explanations

terms related to military vessels or ships

oai_token-act-pair · gpt-3.5-turbo

repeated mentions of "cruiser" and various forms of the word "cruise."

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

è¦ļéĨĴ

-0.75

 McCabe

-0.71

mable

-0.70

 Stard

-0.65

 Referred

-0.64

 Kush

-0.64

 Mellon

-0.62

raised

-0.61

ynasty

-0.58

CLE

-0.57

POSITIVE LOGITS

cially

1.39

isers

1.37

ciating

1.25

cible

1.22

cial

1.20

isin

1.13

ises

1.11

cious

1.05

ising

1.03

fty

1.00

Activations Density 0.046%

terms related to military vessels or ships

repeated mentions of "cruiser" and various forms of the word "cruise."

No Comments

No Known Activations