INDEX

Explanations

phrases related to mentions of a place or person named "Ho"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "Ho" and its variations associated with events or narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

ications

-0.71

CPC

-0.69

 totality

-0.68

 Defin

-0.67

icate

-0.65

 nucleus

-0.65

CTR

-0.65

ication

-0.64

ifications

-0.62

 Commonwealth

-0.61

POSITIVE LOGITS

ppy

1.22

arding

1.20

pper

1.17

pping

1.07

LLOW

1.05

gey

1.05

oney

1.03

eful

1.03

pped

1.00

pps

1.00

Activations Density 0.025%

phrases related to mentions of a place or person named "Ho"

occurrences of the word "Ho" and its variations associated with events or narratives

No Comments

No Known Activations