INDEX

Explanations

phrases related to severe weather events

oai_token-act-pair · gpt-3.5-turbo

references to various types of storms

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

guyen

-0.99

ibaba

-0.86

cius

-0.84

pires

-0.80

usable

-0.72

heastern

-0.71

buquerque

-0.70

reditary

-0.70

 carbohyd

-0.70

rero

-0.70

POSITIVE LOGITS

storm

1.33

storms

0.97

tro

0.90

è¦ļéĨĴ

0.90

burst

0.87

arding

0.85

 Sandy

0.82

 Deploy

0.81

Storm

0.79

 Storm

0.78

Activations Density 0.011%

phrases related to severe weather events

references to various types of storms

No Comments

No Known Activations