INDEX

Explanations

phrases related to a person named "Nik"

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Nik" or variations of it

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

LOAD

-0.81

GROUND

-0.76

è¦ļéĨĴ

-0.72

-0.71

HAHAHAHA

-0.67

heads

-0.67

 actionGroup

-0.66

 Cellular

-0.66

inventoryQuantity

-0.65

BACK

-0.65

POSITIVE LOGITS

aido

1.25

opol

1.07

ita

1.02

olas

1.01

orius

0.99

elsen

0.99

umar

0.95

onite

0.95

eties

0.95

seys

0.93

Activations Density 0.011%

phrases related to a person named "Nik"

mentions of the name "Nik" or variations of it

No Comments

No Known Activations