INDEX

Explanations

references to eating utensils, particularly spoons

oai_token-act-pair · gpt-3.5-turbo

utensils and implements used in cooking or food preparation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ALE

-0.72

UAE

-0.71

 Honour

-0.68

IST

-0.66

izons

-0.65

Hom

-0.64

ndum

-0.64

avid

-0.63

IST

-0.62

LAN

-0.62

POSITIVE LOGITS

 spoon

1.10

 Spoon

1.02

ful

1.01

edIn

0.99

pipe

0.85

knife

0.80

washer

0.79

abwe

0.78

cup

0.77

bling

0.76

Activations Density 0.007%

references to eating utensils, particularly spoons

utensils and implements used in cooking or food preparation

No Comments

No Known Activations