INDEX

Explanations

words related to the usage or consumption of various items or substances

oai_token-act-pair · gpt-3.5-turbo

words and phrases related to various forms of usage and application

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ĸļ

-0.79

 Lumpur

-0.71

çĦ

-0.68

wagen

-0.60

cknowled

-0.60

 drawer

-0.58

 Irving

-0.58

 Blasio

-0.58

bye

-0.57

å§

-0.57

POSITIVE LOGITS

catentry

0.82

olia

0.72

omnia

0.72

QL

0.71

ions

0.68

aneous

0.65

aukee

0.64

ION

0.64

enza

0.63

arious

0.62

Activations Density 0.050%

words related to the usage or consumption of various items or substances

words and phrases related to various forms of usage and application

No Comments

No Known Activations